In this paper,potent index of an element and pseudo clean rings are considered.Some properties and examples of pseudo clean rings are given.We also show that Zm is pseudo clean for every 2≤m∈Z and pseudo clean rings...In this paper,potent index of an element and pseudo clean rings are considered.Some properties and examples of pseudo clean rings are given.We also show that Zm is pseudo clean for every 2≤m∈Z and pseudo clean rings are clean.Furthermore,we prove pseudo clean rings are directly finite and have stable range one.展开更多
Face Presentation Attack Detection(fPAD)plays a vital role in securing face recognition systems against various presentation attacks.While supervised learning-based methods demonstrate effectiveness,they are prone to ...Face Presentation Attack Detection(fPAD)plays a vital role in securing face recognition systems against various presentation attacks.While supervised learning-based methods demonstrate effectiveness,they are prone to overfitting to known attack types and struggle to generalize to novel attack scenarios.Recent studies have explored formulating fPAD as an anomaly detection problem or one-class classification task,enabling the training of generalized models for unknown attack detection.However,conventional anomaly detection approaches encounter difficulties in precisely delineating the boundary between bonafide samples and unknown attacks.To address this challenge,we propose a novel framework focusing on unknown attack detection using exclusively bonafide facial data during training.The core innovation lies in our pseudo-negative sample synthesis(PNSS)strategy,which facilitates learning of compact decision boundaries between bonafide faces and potential attack variations.Specifically,PNSS generates synthetic negative samples within low-likelihood regions of the bonafide feature space to represent diverse unknown attack patterns.To overcome the inherent imbalance between positive and synthetic negative samples during iterative training,we implement a dual-loss mechanism combining focal loss for classification optimization with pairwise confusion loss as a regularizer.This architecture effectively mitigates model bias towards bonafide samples while maintaining discriminative power.Comprehensive evaluations across three benchmark datasets validate the framework’s superior performance.Notably,our PNSS achieves 8%–18% average classification error rate(ACER)reduction compared with state-of-the-art one-class fPAD methods in cross-dataset evaluations on Idiap Replay-Attack and MSU-MFSD datasets.展开更多
The unsupervised vehicle re-identification task aims at identifying specific vehicles in surveillance videos without utilizing annotation information.Due to the higher similarity in appearance between vehicles compare...The unsupervised vehicle re-identification task aims at identifying specific vehicles in surveillance videos without utilizing annotation information.Due to the higher similarity in appearance between vehicles compared to pedestrians,pseudo-labels generated through clustering are ineffective in mitigating the impact of noise,and the feature distance between inter-class and intra-class has not been adequately improved.To address the aforementioned issues,we design a dual contrastive learning method based on knowledge distillation.During each iteration,we utilize a teacher model to randomly partition the entire dataset into two sub-domains based on clustering pseudo-label categories.By conducting contrastive learning between the two student models,we extract more discernible vehicle identity cues to improve the problem of imbalanced data distribution.Subsequently,we propose a context-aware pseudo label refinement strategy that leverages contextual features by progressively associating granularity information from different bottleneck blocks.To produce more trustworthy pseudo-labels and lessen noise interference during the clustering process,the context-aware scores are obtained by calculating the similarity between global features and contextual ones,which are subsequently added to the pseudo-label encoding process.The proposed method has achieved excellent performance in overcoming label noise and optimizing data distribution through extensive experimental results on publicly available datasets.展开更多
In this paper,the existence,uniqueness,asymptotic and global exponential stability of pseudo almost automorphic solution for a class of delayed Lasota-Wazewska model with impulsive effects are established by applying ...In this paper,the existence,uniqueness,asymptotic and global exponential stability of pseudo almost automorphic solution for a class of delayed Lasota-Wazewska model with impulsive effects are established by applying an appropriate fixed point theorem and Lyapunov functional method.Finally,a numerical example with simulation is given to illuminate our theoretical results.展开更多
In this paper,we study the existence of pseudo S-asymptotically ω-periodic mild solutions of abstract partial neutral differential equations in Banach spaces.By using the principle of Banach contractive mapping,the e...In this paper,we study the existence of pseudo S-asymptotically ω-periodic mild solutions of abstract partial neutral differential equations in Banach spaces.By using the principle of Banach contractive mapping,the existence and uniqueness of pseudo S-asymptotically ω-periodic mild solutions of abstract partial neutral differential equations are obtained.To illustrate the ab-stract result,a concrete example is given.展开更多
Traditional Chinese medicine(TCM),especially the plant-based,represents complex chemical system containing various primary and secondary metabolites.These botanical metabolites are structurally diversified and exhibit...Traditional Chinese medicine(TCM),especially the plant-based,represents complex chemical system containing various primary and secondary metabolites.These botanical metabolites are structurally diversified and exhibit significant difference in the acidity,alkalinity,molecular weight,polarity,and content,etc,which thus poses great challenges in assessing the quality of TCM[1].展开更多
Wellens’ syndrome is defined by specific T-wave inversions in the precordial leads of the electrocardiogram (ECG),which are indicative of acute anterior myocardial ischemia caused by severe proximal stenosis of the l...Wellens’ syndrome is defined by specific T-wave inversions in the precordial leads of the electrocardiogram (ECG),which are indicative of acute anterior myocardial ischemia caused by severe proximal stenosis of the left anterior descending (LAD)artery.If not promptly treated,approximately 75%of patients with Wellens’ syndrome may experience extensive anterior wall myocardial infarction or sudden cardiac death within days to weeks.^([1,2]) Although the characteristic ECG changes associated with Wellens’syndrome are highly suggestive of LAD occlusion,there are rare instances in which similar ECG alterations are observed in the absence of LAD stenosis,a phenomenon referred to as pseudo-Wellens’ syndrome.The precise pathophysiological mechanisms underlying this syndrome remain unclear.Here,we present a patient with a myocardial bridge who presented a typical Wellens’ECG pattern.展开更多
This paper,evaluate the effectiveness of a proposed speed loop pseudo derivative feedforward(PDFF)controller-based direct torque controller(DTC)for a PMSM drive against the performance of existing PI speed controller-...This paper,evaluate the effectiveness of a proposed speed loop pseudo derivative feedforward(PDFF)controller-based direct torque controller(DTC)for a PMSM drive against the performance of existing PI speed controller-based DTC and hysteresis current controller(HCC).The proposed PDFF-based speed regulator effectively reduces oscillation and overshoot associated with rotor angular speed,electromagnetic torque,and stator current.Two case studies,one using forward-to-reverse motoring operation and the other involving reverse-to-forward braking operation,has been validated to show the effectiveness of the proposed control strategy.The proposed controller's superior performance is demonstrated through experimental verification utilizing an FPGA controller for a 1.5 kW PMSM drive laboratory prototype.展开更多
This paper provides a nonlinear pseudo-hyperbolic partial differential equation with non-local conditions.Despite the importance of this problem,the exact solution to this problem is rare in the literature.Therefore,t...This paper provides a nonlinear pseudo-hyperbolic partial differential equation with non-local conditions.Despite the importance of this problem,the exact solution to this problem is rare in the literature.Therefore,the Laplace-Adomian Decomposition Method(LADM)is used to provide a new approach to solving this problem.Additionally,we give a comparison between the exact and approximate solutions at various points with absolute error.The obtained result showed that the proposed method is effective and accurate for this problem and can be used for many other evolution of nonlinear equations in mathematical physics.展开更多
Pseudo Human Settlements(PHS)are a fundamental element in human settlements geography,serving as an innovative frontier in the exploration of human–land relationships.Since entering the information age,PHS have emerg...Pseudo Human Settlements(PHS)are a fundamental element in human settlements geography,serving as an innovative frontier in the exploration of human–land relationships.Since entering the information age,PHS have emerged as a new catalyst for people's lives and urban development.Based on the Baidu Index,cold hot spot analysis and the Pearson correlation coefficient method were used to evaluate the spatiotemporal variation characteristics of the development of the quality of PHS at different levels in the three provinces of Northeast China(TPNC)during 2011–2022 and to characterize the influence of the system and factors.The results indicated that:1)temporally,PHS exhibits significant fluctuations,with an overall pattern of rapid increase followed by a gradual decline;2)spatially,PHS is marked by regional differentiation,with“three-core”dominance and a“cluster-like”distribution;3)systematically,the five major PHS systems generally exhibit an ascending and then a descending trend;4)in terms of influence,the socialization system serves as the core influence of PHS,with WeChat,JD.COM,and others are identified as the core influencing factors of subsystems.The findings of this study can provide scientific guidance for diversifying approaches to human settlements,promoting sustainable urban development,and revitalizing Northeast China.展开更多
Motor imagery(MI)based electroencephalogram(EEG)represents a frontier in enabling direct neural control of external devices and advancing neural rehabilitation.This study introduces a novel time embedding technique,te...Motor imagery(MI)based electroencephalogram(EEG)represents a frontier in enabling direct neural control of external devices and advancing neural rehabilitation.This study introduces a novel time embedding technique,termed traveling-wave based time embedding,utilized as a pseudo channel to enhance the decoding accuracy of MI-EEG signals across various neural network architectures.Unlike traditional neural network methods that fail to account for the temporal dynamics in MI-EEG in individual difference,our approach captures time-related changes for different participants based on a priori knowledge.Through extensive experimentation with multiple participants,we demonstrate that this method not only improves classification accuracy but also exhibits greater adaptability to individual differences compared to position encoding used in Transformer architecture.Significantly,our results reveal that traveling-wave based time embedding crucially enhances decoding accuracy,particularly for participants typically considered“EEG-illiteracy”.As a novel direction in EEG research,the traveling-wave based time embedding not only offers fresh insights for neural network decoding strategies but also expands new avenues for research into attention mechanisms in neuroscience and a deeper understanding of EEG signals.展开更多
The specific energy of Li metal batteries(LMBs)can be improved by using high‐voltage cathode materials;however,achieving long‐term stable cycling performance in the corresponding system is particularly challenging f...The specific energy of Li metal batteries(LMBs)can be improved by using high‐voltage cathode materials;however,achieving long‐term stable cycling performance in the corresponding system is particularly challenging for the liquid electrolyte.Herein,a novel pseudo‐oversaturated electrolyte(POSE)is prepared by introducing 1,1,2,2‐tetrafluoroethyl‐2,2,3,3‐tetrafluoropropyl ether(TTE)to adjust the coordination structure between diglyme(G2)and lithium bis(trifluoromethanesulfonyl)imide(LiTFSI).Surprisingly,although TTE shows little solubility to LiTFSI,the molar ratio between LiTFSI and G2 in the POSE can be increased to 1:1,which is much higher than that of the saturation state,1:2.8.Simulation and experimental results prove that TTE promotes closer contact of the G2 molecular with Li^(+)in the POSE.Moreover,it also participates in the formation of electrolyte/electrode interphases.The electrolyte shows outstanding compatibility with both the Li metal anode and typical high‐voltage cathodes.Li||Li symmetric cells show a long life of more than 2000 h at 1 mA cm^(−2),1 mAh cm^(−2).In the meantime,Li||LiNi_(0.8)Co_(0.1)Mn_(0.1)O_(2)(NCM811)cell with the POSE shows a high reversible capacity of 134.8 mAh g^(−1 )after 900 cycles at 4.5 V,1 C rate.The concept of POSE can provide new insight into the Li^(+)solvation structure and in the design of advanced electrolytes for LMBs.展开更多
In this paper,we firstly recall some basic results on pseudo S-asymptotically(ω,c)-periodic functions and Sobolev type fractional differential equation.We secondly investigate some existence of pseudo S-asymptotical...In this paper,we firstly recall some basic results on pseudo S-asymptotically(ω,c)-periodic functions and Sobolev type fractional differential equation.We secondly investigate some existence of pseudo S-asymptotically(ω,c)-periodic solutions for a semilinear fractional differential equations of Sobolev type.We finally present a simple example.展开更多
图像异常检测旨在识别并定位图像中的异常区域,针对现有算法中不同层次特征信息利用不充分的问题,提出了基于多层次特征融合网络的图像异常检测算法。通过使用融合了异常先验知识的伪异常数据生成算法,对训练集进行了异常数据扩充,将异...图像异常检测旨在识别并定位图像中的异常区域,针对现有算法中不同层次特征信息利用不充分的问题,提出了基于多层次特征融合网络的图像异常检测算法。通过使用融合了异常先验知识的伪异常数据生成算法,对训练集进行了异常数据扩充,将异常检测任务转化为监督学习任务;构建了多层次特征融合网络,将神经网络中不同层次特征进行融合,丰富了特征中的低层纹理信息和高层语义信息,使得用于异常检测的特征更具区分性;训练时,设计了分数约束损失和一致性约束损失,并结合特征约束损失对整个网络模型进行训练。实验结果表明,MVTec数据集上图像级检测接收机工作特性曲线下面积(area under the receiver operating characteristic, AUROC)平均值为98.7%,像素级定位AUROC平均值为97.9%,每区域重叠率平均值为94.2%,均高于现有的异常检测算法。展开更多
基金Supported by National Natural Science Foundation of China(12301041)。
文摘In this paper,potent index of an element and pseudo clean rings are considered.Some properties and examples of pseudo clean rings are given.We also show that Zm is pseudo clean for every 2≤m∈Z and pseudo clean rings are clean.Furthermore,we prove pseudo clean rings are directly finite and have stable range one.
基金supported in part by the National Natural Science Foundation of China under Grants 61972267,and 61772070in part by the Natural Science Foundation of Hebei Province under Grant F2024210005.
文摘Face Presentation Attack Detection(fPAD)plays a vital role in securing face recognition systems against various presentation attacks.While supervised learning-based methods demonstrate effectiveness,they are prone to overfitting to known attack types and struggle to generalize to novel attack scenarios.Recent studies have explored formulating fPAD as an anomaly detection problem or one-class classification task,enabling the training of generalized models for unknown attack detection.However,conventional anomaly detection approaches encounter difficulties in precisely delineating the boundary between bonafide samples and unknown attacks.To address this challenge,we propose a novel framework focusing on unknown attack detection using exclusively bonafide facial data during training.The core innovation lies in our pseudo-negative sample synthesis(PNSS)strategy,which facilitates learning of compact decision boundaries between bonafide faces and potential attack variations.Specifically,PNSS generates synthetic negative samples within low-likelihood regions of the bonafide feature space to represent diverse unknown attack patterns.To overcome the inherent imbalance between positive and synthetic negative samples during iterative training,we implement a dual-loss mechanism combining focal loss for classification optimization with pairwise confusion loss as a regularizer.This architecture effectively mitigates model bias towards bonafide samples while maintaining discriminative power.Comprehensive evaluations across three benchmark datasets validate the framework’s superior performance.Notably,our PNSS achieves 8%–18% average classification error rate(ACER)reduction compared with state-of-the-art one-class fPAD methods in cross-dataset evaluations on Idiap Replay-Attack and MSU-MFSD datasets.
基金supported by the National Natural Science Foundation of China under Grant Nos.62461037,62076117 and 62166026the Jiangxi Provincial Natural Science Foundation under Grant Nos.20224BAB212011,20232BAB202051,20232BAB212008 and 20242BAB25078the Jiangxi Provincial Key Laboratory of Virtual Reality under Grant No.2024SSY03151.
文摘The unsupervised vehicle re-identification task aims at identifying specific vehicles in surveillance videos without utilizing annotation information.Due to the higher similarity in appearance between vehicles compared to pedestrians,pseudo-labels generated through clustering are ineffective in mitigating the impact of noise,and the feature distance between inter-class and intra-class has not been adequately improved.To address the aforementioned issues,we design a dual contrastive learning method based on knowledge distillation.During each iteration,we utilize a teacher model to randomly partition the entire dataset into two sub-domains based on clustering pseudo-label categories.By conducting contrastive learning between the two student models,we extract more discernible vehicle identity cues to improve the problem of imbalanced data distribution.Subsequently,we propose a context-aware pseudo label refinement strategy that leverages contextual features by progressively associating granularity information from different bottleneck blocks.To produce more trustworthy pseudo-labels and lessen noise interference during the clustering process,the context-aware scores are obtained by calculating the similarity between global features and contextual ones,which are subsequently added to the pseudo-label encoding process.The proposed method has achieved excellent performance in overcoming label noise and optimizing data distribution through extensive experimental results on publicly available datasets.
文摘In this paper,the existence,uniqueness,asymptotic and global exponential stability of pseudo almost automorphic solution for a class of delayed Lasota-Wazewska model with impulsive effects are established by applying an appropriate fixed point theorem and Lyapunov functional method.Finally,a numerical example with simulation is given to illuminate our theoretical results.
基金Supported by the National Natural Science Foundation of China(11226337)the Science and Technology Research Projects of Henan Education Committee(22B110017).
文摘In this paper,we study the existence of pseudo S-asymptotically ω-periodic mild solutions of abstract partial neutral differential equations in Banach spaces.By using the principle of Banach contractive mapping,the existence and uniqueness of pseudo S-asymptotically ω-periodic mild solutions of abstract partial neutral differential equations are obtained.To illustrate the ab-stract result,a concrete example is given.
文摘Traditional Chinese medicine(TCM),especially the plant-based,represents complex chemical system containing various primary and secondary metabolites.These botanical metabolites are structurally diversified and exhibit significant difference in the acidity,alkalinity,molecular weight,polarity,and content,etc,which thus poses great challenges in assessing the quality of TCM[1].
基金supported by a grant from the Science and Technology Fund of Tianjin Municipal Education Commission(2021KJ216)。
文摘Wellens’ syndrome is defined by specific T-wave inversions in the precordial leads of the electrocardiogram (ECG),which are indicative of acute anterior myocardial ischemia caused by severe proximal stenosis of the left anterior descending (LAD)artery.If not promptly treated,approximately 75%of patients with Wellens’ syndrome may experience extensive anterior wall myocardial infarction or sudden cardiac death within days to weeks.^([1,2]) Although the characteristic ECG changes associated with Wellens’syndrome are highly suggestive of LAD occlusion,there are rare instances in which similar ECG alterations are observed in the absence of LAD stenosis,a phenomenon referred to as pseudo-Wellens’ syndrome.The precise pathophysiological mechanisms underlying this syndrome remain unclear.Here,we present a patient with a myocardial bridge who presented a typical Wellens’ECG pattern.
基金supported by Prince Sultan University,Riyadh,Saudi Arabia,under research grant SEED-2022-CE-95。
文摘This paper,evaluate the effectiveness of a proposed speed loop pseudo derivative feedforward(PDFF)controller-based direct torque controller(DTC)for a PMSM drive against the performance of existing PI speed controller-based DTC and hysteresis current controller(HCC).The proposed PDFF-based speed regulator effectively reduces oscillation and overshoot associated with rotor angular speed,electromagnetic torque,and stator current.Two case studies,one using forward-to-reverse motoring operation and the other involving reverse-to-forward braking operation,has been validated to show the effectiveness of the proposed control strategy.The proposed controller's superior performance is demonstrated through experimental verification utilizing an FPGA controller for a 1.5 kW PMSM drive laboratory prototype.
文摘This paper provides a nonlinear pseudo-hyperbolic partial differential equation with non-local conditions.Despite the importance of this problem,the exact solution to this problem is rare in the literature.Therefore,the Laplace-Adomian Decomposition Method(LADM)is used to provide a new approach to solving this problem.Additionally,we give a comparison between the exact and approximate solutions at various points with absolute error.The obtained result showed that the proposed method is effective and accurate for this problem and can be used for many other evolution of nonlinear equations in mathematical physics.
基金National Natural Science Foundation of China,No.42471246,No.42201221Liaoning Province Natural Science,No.2023-MS-254+1 种基金Liaoning Province Social Science Planning Fund Project,No.L22CJY016Dalian Federation of Social Sciences,No.2022dlskzd037。
文摘Pseudo Human Settlements(PHS)are a fundamental element in human settlements geography,serving as an innovative frontier in the exploration of human–land relationships.Since entering the information age,PHS have emerged as a new catalyst for people's lives and urban development.Based on the Baidu Index,cold hot spot analysis and the Pearson correlation coefficient method were used to evaluate the spatiotemporal variation characteristics of the development of the quality of PHS at different levels in the three provinces of Northeast China(TPNC)during 2011–2022 and to characterize the influence of the system and factors.The results indicated that:1)temporally,PHS exhibits significant fluctuations,with an overall pattern of rapid increase followed by a gradual decline;2)spatially,PHS is marked by regional differentiation,with“three-core”dominance and a“cluster-like”distribution;3)systematically,the five major PHS systems generally exhibit an ascending and then a descending trend;4)in terms of influence,the socialization system serves as the core influence of PHS,with WeChat,JD.COM,and others are identified as the core influencing factors of subsystems.The findings of this study can provide scientific guidance for diversifying approaches to human settlements,promoting sustainable urban development,and revitalizing Northeast China.
文摘Motor imagery(MI)based electroencephalogram(EEG)represents a frontier in enabling direct neural control of external devices and advancing neural rehabilitation.This study introduces a novel time embedding technique,termed traveling-wave based time embedding,utilized as a pseudo channel to enhance the decoding accuracy of MI-EEG signals across various neural network architectures.Unlike traditional neural network methods that fail to account for the temporal dynamics in MI-EEG in individual difference,our approach captures time-related changes for different participants based on a priori knowledge.Through extensive experimentation with multiple participants,we demonstrate that this method not only improves classification accuracy but also exhibits greater adaptability to individual differences compared to position encoding used in Transformer architecture.Significantly,our results reveal that traveling-wave based time embedding crucially enhances decoding accuracy,particularly for participants typically considered“EEG-illiteracy”.As a novel direction in EEG research,the traveling-wave based time embedding not only offers fresh insights for neural network decoding strategies but also expands new avenues for research into attention mechanisms in neuroscience and a deeper understanding of EEG signals.
基金Subsidy for Hebei Key Laboratory of Applied Chemistry after Operation Performance,Grant/Award Number:22567616HNatural Science Foundation of Hebei Province of China,Grant/Award Number:B2020103028+3 种基金Science Fund for Creative Research Groups of the National Natural Science Foundation of China,Grant/Award Number:21921005National Key Research and Development Program of China,Grant/Award Number:2021YFB2400300Beijing Municipal Natural Science Foundation Project,Grant/Award Number:2222031National Natural Science Foundation of China,Grant/Award Numbers:52174281,21808228。
文摘The specific energy of Li metal batteries(LMBs)can be improved by using high‐voltage cathode materials;however,achieving long‐term stable cycling performance in the corresponding system is particularly challenging for the liquid electrolyte.Herein,a novel pseudo‐oversaturated electrolyte(POSE)is prepared by introducing 1,1,2,2‐tetrafluoroethyl‐2,2,3,3‐tetrafluoropropyl ether(TTE)to adjust the coordination structure between diglyme(G2)and lithium bis(trifluoromethanesulfonyl)imide(LiTFSI).Surprisingly,although TTE shows little solubility to LiTFSI,the molar ratio between LiTFSI and G2 in the POSE can be increased to 1:1,which is much higher than that of the saturation state,1:2.8.Simulation and experimental results prove that TTE promotes closer contact of the G2 molecular with Li^(+)in the POSE.Moreover,it also participates in the formation of electrolyte/electrode interphases.The electrolyte shows outstanding compatibility with both the Li metal anode and typical high‐voltage cathodes.Li||Li symmetric cells show a long life of more than 2000 h at 1 mA cm^(−2),1 mAh cm^(−2).In the meantime,Li||LiNi_(0.8)Co_(0.1)Mn_(0.1)O_(2)(NCM811)cell with the POSE shows a high reversible capacity of 134.8 mAh g^(−1 )after 900 cycles at 4.5 V,1 C rate.The concept of POSE can provide new insight into the Li^(+)solvation structure and in the design of advanced electrolytes for LMBs.
基金supported by NSF of Shaanxi Province(Grant No.2023-JC-YB-011).
文摘In this paper,we firstly recall some basic results on pseudo S-asymptotically(ω,c)-periodic functions and Sobolev type fractional differential equation.We secondly investigate some existence of pseudo S-asymptotically(ω,c)-periodic solutions for a semilinear fractional differential equations of Sobolev type.We finally present a simple example.
文摘图像异常检测旨在识别并定位图像中的异常区域,针对现有算法中不同层次特征信息利用不充分的问题,提出了基于多层次特征融合网络的图像异常检测算法。通过使用融合了异常先验知识的伪异常数据生成算法,对训练集进行了异常数据扩充,将异常检测任务转化为监督学习任务;构建了多层次特征融合网络,将神经网络中不同层次特征进行融合,丰富了特征中的低层纹理信息和高层语义信息,使得用于异常检测的特征更具区分性;训练时,设计了分数约束损失和一致性约束损失,并结合特征约束损失对整个网络模型进行训练。实验结果表明,MVTec数据集上图像级检测接收机工作特性曲线下面积(area under the receiver operating characteristic, AUROC)平均值为98.7%,像素级定位AUROC平均值为97.9%,每区域重叠率平均值为94.2%,均高于现有的异常检测算法。
