The classification of respiratory sounds is crucial in diagnosing and monitoring respiratory diseases.However,auscultation is highly subjective,making it challenging to analyze respiratory sounds accurately.Although d...The classification of respiratory sounds is crucial in diagnosing and monitoring respiratory diseases.However,auscultation is highly subjective,making it challenging to analyze respiratory sounds accurately.Although deep learning has been increasingly applied to this task,most existing approaches have primarily relied on supervised learning.Since supervised learning requires large amounts of labeled data,recent studies have explored self-supervised and semi-supervised methods to overcome this limitation.However,these approaches have largely assumed a closedset setting,where the classes present in the unlabeled data are considered identical to those in the labeled data.In contrast,this study explores an open-set semi-supervised learning setting,where the unlabeled data may contain additional,unknown classes.To address this challenge,a distance-based prototype network is employed to classify respiratory sounds in an open-set setting.In the first stage,the prototype network is trained using labeled and unlabeled data to derive prototype representations of known classes.In the second stage,distances between unlabeled data and known class prototypes are computed,and samples exceeding an adaptive threshold are identified as unknown.A new prototype is then calculated for this unknown class.In the final stage,semi-supervised learning is employed to classify labeled and unlabeled data into known and unknown classes.Compared to conventional closed-set semisupervised learning approaches,the proposed method achieved an average classification accuracy improvement of 2%–5%.Additionally,in cases of data scarcity,utilizing unlabeled data further improved classification performance by 6%–8%.The findings of this study are expected to significantly enhance respiratory sound classification performance in practical clinical settings.展开更多
There are all kinds of unknown and known signals in the actual electromagnetic environment,which hinders the development of practical cognitive radio applications.However,most existing signal recognition models are di...There are all kinds of unknown and known signals in the actual electromagnetic environment,which hinders the development of practical cognitive radio applications.However,most existing signal recognition models are difficult to discover unknown signals while recognizing known ones.In this paper,a compact manifold mixup feature-based open-set recognition approach(OR-CMMF)is proposed to address the above problem.First,the proposed approach utilizes the center loss to constrain decision boundaries so that it obtains the compact latent signal feature representations and extends the low-confidence feature space.Second,the latent signal feature representations are used to construct synthetic representations as substitutes for unknown categories of signals.Then,these constructed representations can occupy the extended low-confidence space.Finally,the proposed approach applies the distillation loss to adjust the decision boundaries between the known categories signals and the constructed unknown categories substitutes so that it accurately discovers unknown signals.The OR-CMMF approach outperformed other state-of-the-art open-set recognition methods in comprehensive recognition performance and running time,as demonstrated by simulation experiments on two public datasets RML2016.10a and ORACLE.展开更多
In the traditional pattern classification method,it usually assumes that the object to be classified must lie in one of given(known)classes of the training data set.However,the training data set may not contain the cl...In the traditional pattern classification method,it usually assumes that the object to be classified must lie in one of given(known)classes of the training data set.However,the training data set may not contain the class of some objects in practice,and this is considered as an Open-Set Recognition(OSR)problem.In this paper,we propose a new progressive open-set recognition method with adaptive probability threshold.Both the labeled training data and the test data(objects to be classified)are put into a common data set,and the k-Nearest Neighbors(k-NNs)of each object are sought in this common set.Then,we can determine the probability of object lying in the given classes.If the majority of k-NNs of the object are from labeled training data,this object quite likely belongs to one of the given classes,and the density of the object and its neighbors is taken into account here.However,when most of k-NNs are from the unlabeled test data set,the class of object is considered very uncertain because the class of test data is unknown,and this object cannot be classified in this step.Once the objects belonging to known classes with high probability are all found,we re-calculate the probability of the other uncertain objects belonging to known classes based on the labeled training data and the objects marked with the estimated probability.Such iteration will stop when the probabilities of all the objects belonging to known classes are not changed.Then,a modified Otsu’s method is employed to adaptively seek the probability threshold for the final classification.If the probability of object belonging to known classes is smaller than this threshold,it will be assigned to the ignorant(unknown)class that is not included in training data set.The other objects will be committed to a specific class.The effectiveness of the proposed method has been validated using some experiments.展开更多
Open-set recognition(OSR)is a realistic problem in wireless signal recogni-tion,which means that during the inference phase there may appear unknown classes not seen in the training phase.The method of intra-class spl...Open-set recognition(OSR)is a realistic problem in wireless signal recogni-tion,which means that during the inference phase there may appear unknown classes not seen in the training phase.The method of intra-class splitting(ICS)that splits samples of known classes to imitate unknown classes has achieved great performance.However,this approach relies too much on the predefined splitting ratio and may face huge performance degradation in new environment.In this paper,we train a multi-task learning(MTL)net-work based on the characteristics of wireless signals to improve the performance in new scenes.Besides,we provide a dynamic method to decide the splitting ratio per class to get more precise outer samples.To be specific,we make perturbations to the sample from the center of one class toward its adversarial direction and the change point of confidence scores during this process is used as the splitting threshold.We conduct several experi-ments on one wireless signal dataset collected at 2.4 GHz ISM band by LimeSDR and one open modulation recognition dataset,and the analytical results demonstrate the effective-ness of the proposed method.展开更多
随着各种新型雷达的出现或战时预留模式的采用,真实的战场电磁环境将越加复杂,大概率会出现种类未知且参数突变的雷达调制信号,对现有的调制方式识别算法带来严峻挑战。对此,分析雷达调制方式“未知”对识别结果的影响机理,将开集差分...随着各种新型雷达的出现或战时预留模式的采用,真实的战场电磁环境将越加复杂,大概率会出现种类未知且参数突变的雷达调制信号,对现有的调制方式识别算法带来严峻挑战。对此,分析雷达调制方式“未知”对识别结果的影响机理,将开集差分分布对齐(distribution alignment with open set difference,DAOD)算法引入雷达调制方式识别领域,设计具体应用的技术方案,并针对DAOD算法所需参数依靠先验知识或者试探选取问题,利用蜣螂优化(dung beetle optimizer,DBO)算法进行参数优化。仿真结果表明:在单个雷达调制方式未知情形下,精确度Accuracy和F-measure分值的平均值分别可达91.34%和95.11%;在多个雷达调制方式未知情形下,Accuracy和F-measure的平均值分别可达91.37%、93.69%;与DAOD算法相比,上述结果分别提升了3.77%、1.83%、21.17%和12.06%。因此,DBO-DAOD算法可有效提升未知雷达调制方式的识别率。展开更多
DDoS attacks represent one of the most pervasive and evolving threats in cybersecurity,capable of crippling critical infrastructures and disrupting services globally.As networks continue to expand and threats become m...DDoS attacks represent one of the most pervasive and evolving threats in cybersecurity,capable of crippling critical infrastructures and disrupting services globally.As networks continue to expand and threats become more sophisticated,there is an urgent need for Intrusion Detection Systems(IDS)capable of handling these challenges effectively.Traditional IDS models frequently have difficulties in detecting new or changing attack patterns since they heavily depend on existing characteristics.This paper presents a novel approach for detecting unknown Distributed Denial of Service(DDoS)attacks by integrating Sliced Iterative Normalizing Flows(SINF)into IDS.SINF utilizes the Sliced Wasserstein distance to repeatedly modify probability distributions,enabling better management of high-dimensional data when there are only a few samples available.The unique architecture of SINF ensures efficient density estimation and robust sample generation,enabling IDS to adapt dynamically to emerging threats without relying heavily on predefined signatures or extensive retraining.By incorporating Open-Set Recognition(OSR)techniques,this method improves the system’s ability to detect both known and unknown attacks while maintaining high detection performance.The experimental evaluation on CICIDS2017 and CICDDoS2019 datasets demonstrates that the proposed system achieves an accuracy of 99.85%for known attacks and an F1 score of 99.99%after incremental learning for unknown attacks.The results clearly demonstrate the system’s strong generalization capability across unseen attacks while maintaining the computational efficiency required for real-world deployment.展开更多
面对新工业革命背景下算力复杂性上升与定制化需求加剧的挑战,开源硬件正成为打破封闭架构限制、增强技术自主可控能力的重要途径.重点关注了以RISC-Ⅴ(Reduced Instruction Set ComputerFive)为代表的开源指令集架构,系统梳理了其生态...面对新工业革命背景下算力复杂性上升与定制化需求加剧的挑战,开源硬件正成为打破封闭架构限制、增强技术自主可控能力的重要途径.重点关注了以RISC-Ⅴ(Reduced Instruction Set ComputerFive)为代表的开源指令集架构,系统梳理了其生态优势和产业价值;同时比较了国内外主要开源项目在设计开放性、系统灵活性及协同创新机制方面的不同特点;从时间维度展开分析,可以明确开源硬件从底层架构创新逐步走向异构融合和场景拓展的发展趋势.研究表明,开源硬件在智能制造、边缘计算、沉浸式终端等关键领域有着广阔的应用前景,能够有效提升算力利用效率,降低开发难度和系统成本.开源硬件正推动芯片设计从封闭模式向共享模式转变,为工业智能化升级和技术安全战略提供新的支撑.展开更多
当深度神经网络(DNN)遇到训练时未遇见的类别的样本时,不能准确地拒绝未知类样本,而开集识别能在准确分类已知类样本同时拒绝未知类样本。目前在开集识别领域,原型学习方法广为应用,然而这些方法都无法同时保证样本分布内的紧凑性和样...当深度神经网络(DNN)遇到训练时未遇见的类别的样本时,不能准确地拒绝未知类样本,而开集识别能在准确分类已知类样本同时拒绝未知类样本。目前在开集识别领域,原型学习方法广为应用,然而这些方法都无法同时保证样本分布内的紧凑性和样本分布间的分离性。因此,提出开放生成与特征优化的开集识别方法(OGFO)。首先,提出开放点的概念,原型点通过DNN学习对应类别样本的固有特征而开放点是各类别原型点的均值。开放点代表未知类的固有特征且占据特征空间的中心区域。特征空间中心区域为未知类样本分布的开放空间;其次,提出基于开放点的特征优化算法(FOA),从而利用开放点强迫相同类别样本内部的分布更加紧凑并且迫使不同类别样本间的分布更加分离;最后,提出基于开放点的生成方法 OGAN(Open Generative Adversarial Network),并使用DNN迫使OGAN生成的未知类样本分布在开放点占据的开放空间中。实验结果表明,相较于基于对抗性反向点学习的开集识别方法(ARPL),OGFO在MNIST、SVHN、CIFAR10和TinyImageNet数据集上的AUROC(Area Under the Receiver Operating Characteristic curve)提升明显,尤其在TinyImageNet数据集上的AUROC上至少提升了3个百分点,在准确率和OSCR(Open Set Classification Rate)上分别至少提升6和5个百分点。可见,OGFO解决了其他方法无法兼顾样本分布内的紧凑性和样本分布间的分离性的问题。展开更多
特征选择是雷达目标识别流程中一个较为关键的环节,通过对原始特征集进行筛选,挑选出其中的优质特征构成新的特征子集,可以有效增加识别准确率,提升识别效率。为了提升开放环境下高分辨距离像(High Range Resolution Profile,HRRP)的识...特征选择是雷达目标识别流程中一个较为关键的环节,通过对原始特征集进行筛选,挑选出其中的优质特征构成新的特征子集,可以有效增加识别准确率,提升识别效率。为了提升开放环境下高分辨距离像(High Range Resolution Profile,HRRP)的识别性能,针对现有特征选择方法基于闭集假设,无法有效应对实际应用中存在库外目标导致的开集识别(Open Set Recognition,OSR)性能下降问题,本文提出了一种基于局部离群因子(Local Outlier Factor,LOF)的HRRP开集识别特征选择方法。首先,从原始HRRP中提取15维特征向量作为原始特征集;其次,该方法引入聚合性概念,并使用LOF作为其度量,通过评估特征子集的聚合性来保证其在OSR时具有最小的开放空间风险。同时,采用重心法评估特征子集的可分性,并使用前向搜索算法优化特征选择过程,确保所选特征子集为维数约束下的最优解。实验结果表明:利用所提方法选择的特征子集在开集环境下识别性能优于现有特征提取方法,提升了开集环境下高分辨距离像的识别性能。展开更多
基金supported by Innovative Human Resource Development for Local Intellectualization Programthrough the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(IITP-2025-RS-2022-00156360).
文摘The classification of respiratory sounds is crucial in diagnosing and monitoring respiratory diseases.However,auscultation is highly subjective,making it challenging to analyze respiratory sounds accurately.Although deep learning has been increasingly applied to this task,most existing approaches have primarily relied on supervised learning.Since supervised learning requires large amounts of labeled data,recent studies have explored self-supervised and semi-supervised methods to overcome this limitation.However,these approaches have largely assumed a closedset setting,where the classes present in the unlabeled data are considered identical to those in the labeled data.In contrast,this study explores an open-set semi-supervised learning setting,where the unlabeled data may contain additional,unknown classes.To address this challenge,a distance-based prototype network is employed to classify respiratory sounds in an open-set setting.In the first stage,the prototype network is trained using labeled and unlabeled data to derive prototype representations of known classes.In the second stage,distances between unlabeled data and known class prototypes are computed,and samples exceeding an adaptive threshold are identified as unknown.A new prototype is then calculated for this unknown class.In the final stage,semi-supervised learning is employed to classify labeled and unlabeled data into known and unknown classes.Compared to conventional closed-set semisupervised learning approaches,the proposed method achieved an average classification accuracy improvement of 2%–5%.Additionally,in cases of data scarcity,utilizing unlabeled data further improved classification performance by 6%–8%.The findings of this study are expected to significantly enhance respiratory sound classification performance in practical clinical settings.
基金fully supported by National Natural Science Foundation of China(61871422)Natural Science Foundation of Sichuan Province(2023NSFSC1422)Central Universities of South west Minzu University(ZYN2022032)。
文摘There are all kinds of unknown and known signals in the actual electromagnetic environment,which hinders the development of practical cognitive radio applications.However,most existing signal recognition models are difficult to discover unknown signals while recognizing known ones.In this paper,a compact manifold mixup feature-based open-set recognition approach(OR-CMMF)is proposed to address the above problem.First,the proposed approach utilizes the center loss to constrain decision boundaries so that it obtains the compact latent signal feature representations and extends the low-confidence feature space.Second,the latent signal feature representations are used to construct synthetic representations as substitutes for unknown categories of signals.Then,these constructed representations can occupy the extended low-confidence space.Finally,the proposed approach applies the distillation loss to adjust the decision boundaries between the known categories signals and the constructed unknown categories substitutes so that it accurately discovers unknown signals.The OR-CMMF approach outperformed other state-of-the-art open-set recognition methods in comprehensive recognition performance and running time,as demonstrated by simulation experiments on two public datasets RML2016.10a and ORACLE.
基金supported by the National Natural Science Foundation of China(Nos.U20B2067).
文摘In the traditional pattern classification method,it usually assumes that the object to be classified must lie in one of given(known)classes of the training data set.However,the training data set may not contain the class of some objects in practice,and this is considered as an Open-Set Recognition(OSR)problem.In this paper,we propose a new progressive open-set recognition method with adaptive probability threshold.Both the labeled training data and the test data(objects to be classified)are put into a common data set,and the k-Nearest Neighbors(k-NNs)of each object are sought in this common set.Then,we can determine the probability of object lying in the given classes.If the majority of k-NNs of the object are from labeled training data,this object quite likely belongs to one of the given classes,and the density of the object and its neighbors is taken into account here.However,when most of k-NNs are from the unlabeled test data set,the class of object is considered very uncertain because the class of test data is unknown,and this object cannot be classified in this step.Once the objects belonging to known classes with high probability are all found,we re-calculate the probability of the other uncertain objects belonging to known classes based on the labeled training data and the objects marked with the estimated probability.Such iteration will stop when the probabilities of all the objects belonging to known classes are not changed.Then,a modified Otsu’s method is employed to adaptively seek the probability threshold for the final classification.If the probability of object belonging to known classes is smaller than this threshold,it will be assigned to the ignorant(unknown)class that is not included in training data set.The other objects will be committed to a specific class.The effectiveness of the proposed method has been validated using some experiments.
文摘Open-set recognition(OSR)is a realistic problem in wireless signal recogni-tion,which means that during the inference phase there may appear unknown classes not seen in the training phase.The method of intra-class splitting(ICS)that splits samples of known classes to imitate unknown classes has achieved great performance.However,this approach relies too much on the predefined splitting ratio and may face huge performance degradation in new environment.In this paper,we train a multi-task learning(MTL)net-work based on the characteristics of wireless signals to improve the performance in new scenes.Besides,we provide a dynamic method to decide the splitting ratio per class to get more precise outer samples.To be specific,we make perturbations to the sample from the center of one class toward its adversarial direction and the change point of confidence scores during this process is used as the splitting threshold.We conduct several experi-ments on one wireless signal dataset collected at 2.4 GHz ISM band by LimeSDR and one open modulation recognition dataset,and the analytical results demonstrate the effective-ness of the proposed method.
文摘随着各种新型雷达的出现或战时预留模式的采用,真实的战场电磁环境将越加复杂,大概率会出现种类未知且参数突变的雷达调制信号,对现有的调制方式识别算法带来严峻挑战。对此,分析雷达调制方式“未知”对识别结果的影响机理,将开集差分分布对齐(distribution alignment with open set difference,DAOD)算法引入雷达调制方式识别领域,设计具体应用的技术方案,并针对DAOD算法所需参数依靠先验知识或者试探选取问题,利用蜣螂优化(dung beetle optimizer,DBO)算法进行参数优化。仿真结果表明:在单个雷达调制方式未知情形下,精确度Accuracy和F-measure分值的平均值分别可达91.34%和95.11%;在多个雷达调制方式未知情形下,Accuracy和F-measure的平均值分别可达91.37%、93.69%;与DAOD算法相比,上述结果分别提升了3.77%、1.83%、21.17%和12.06%。因此,DBO-DAOD算法可有效提升未知雷达调制方式的识别率。
基金supported by the National Science and Technology Council,Taiwan with grant numbers NSTC 112-2221-E-992-045,112-2221-E-992-057-MY3,and 112-2622-8-992-009-TD1.
文摘DDoS attacks represent one of the most pervasive and evolving threats in cybersecurity,capable of crippling critical infrastructures and disrupting services globally.As networks continue to expand and threats become more sophisticated,there is an urgent need for Intrusion Detection Systems(IDS)capable of handling these challenges effectively.Traditional IDS models frequently have difficulties in detecting new or changing attack patterns since they heavily depend on existing characteristics.This paper presents a novel approach for detecting unknown Distributed Denial of Service(DDoS)attacks by integrating Sliced Iterative Normalizing Flows(SINF)into IDS.SINF utilizes the Sliced Wasserstein distance to repeatedly modify probability distributions,enabling better management of high-dimensional data when there are only a few samples available.The unique architecture of SINF ensures efficient density estimation and robust sample generation,enabling IDS to adapt dynamically to emerging threats without relying heavily on predefined signatures or extensive retraining.By incorporating Open-Set Recognition(OSR)techniques,this method improves the system’s ability to detect both known and unknown attacks while maintaining high detection performance.The experimental evaluation on CICIDS2017 and CICDDoS2019 datasets demonstrates that the proposed system achieves an accuracy of 99.85%for known attacks and an F1 score of 99.99%after incremental learning for unknown attacks.The results clearly demonstrate the system’s strong generalization capability across unseen attacks while maintaining the computational efficiency required for real-world deployment.
文摘面对新工业革命背景下算力复杂性上升与定制化需求加剧的挑战,开源硬件正成为打破封闭架构限制、增强技术自主可控能力的重要途径.重点关注了以RISC-Ⅴ(Reduced Instruction Set ComputerFive)为代表的开源指令集架构,系统梳理了其生态优势和产业价值;同时比较了国内外主要开源项目在设计开放性、系统灵活性及协同创新机制方面的不同特点;从时间维度展开分析,可以明确开源硬件从底层架构创新逐步走向异构融合和场景拓展的发展趋势.研究表明,开源硬件在智能制造、边缘计算、沉浸式终端等关键领域有着广阔的应用前景,能够有效提升算力利用效率,降低开发难度和系统成本.开源硬件正推动芯片设计从封闭模式向共享模式转变,为工业智能化升级和技术安全战略提供新的支撑.
文摘当深度神经网络(DNN)遇到训练时未遇见的类别的样本时,不能准确地拒绝未知类样本,而开集识别能在准确分类已知类样本同时拒绝未知类样本。目前在开集识别领域,原型学习方法广为应用,然而这些方法都无法同时保证样本分布内的紧凑性和样本分布间的分离性。因此,提出开放生成与特征优化的开集识别方法(OGFO)。首先,提出开放点的概念,原型点通过DNN学习对应类别样本的固有特征而开放点是各类别原型点的均值。开放点代表未知类的固有特征且占据特征空间的中心区域。特征空间中心区域为未知类样本分布的开放空间;其次,提出基于开放点的特征优化算法(FOA),从而利用开放点强迫相同类别样本内部的分布更加紧凑并且迫使不同类别样本间的分布更加分离;最后,提出基于开放点的生成方法 OGAN(Open Generative Adversarial Network),并使用DNN迫使OGAN生成的未知类样本分布在开放点占据的开放空间中。实验结果表明,相较于基于对抗性反向点学习的开集识别方法(ARPL),OGFO在MNIST、SVHN、CIFAR10和TinyImageNet数据集上的AUROC(Area Under the Receiver Operating Characteristic curve)提升明显,尤其在TinyImageNet数据集上的AUROC上至少提升了3个百分点,在准确率和OSCR(Open Set Classification Rate)上分别至少提升6和5个百分点。可见,OGFO解决了其他方法无法兼顾样本分布内的紧凑性和样本分布间的分离性的问题。
文摘特征选择是雷达目标识别流程中一个较为关键的环节,通过对原始特征集进行筛选,挑选出其中的优质特征构成新的特征子集,可以有效增加识别准确率,提升识别效率。为了提升开放环境下高分辨距离像(High Range Resolution Profile,HRRP)的识别性能,针对现有特征选择方法基于闭集假设,无法有效应对实际应用中存在库外目标导致的开集识别(Open Set Recognition,OSR)性能下降问题,本文提出了一种基于局部离群因子(Local Outlier Factor,LOF)的HRRP开集识别特征选择方法。首先,从原始HRRP中提取15维特征向量作为原始特征集;其次,该方法引入聚合性概念,并使用LOF作为其度量,通过评估特征子集的聚合性来保证其在OSR时具有最小的开放空间风险。同时,采用重心法评估特征子集的可分性,并使用前向搜索算法优化特征选择过程,确保所选特征子集为维数约束下的最优解。实验结果表明:利用所提方法选择的特征子集在开集环境下识别性能优于现有特征提取方法,提升了开集环境下高分辨距离像的识别性能。
