Structural Health Monitoring(SHM)systems have become a crucial tool for the operational management of long tunnels.For immersed tunnels exposed to both traffic loads and the effects of the marine environment,efficient...Structural Health Monitoring(SHM)systems have become a crucial tool for the operational management of long tunnels.For immersed tunnels exposed to both traffic loads and the effects of the marine environment,efficiently identifying abnormal conditions from the extensive unannotated SHM data presents a significant challenge.This study proposed amodel-based approach for anomaly detection and conducted validation and comparative analysis of two distinct temporal predictive models using SHM data from a real immersed tunnel.Firstly,a dynamic predictive model-based anomaly detectionmethod is proposed,which utilizes a rolling time window for modeling to achieve dynamic prediction.Leveraging the assumption of temporal data similarity,an interval prediction value deviation was employed to determine the abnormality of the data.Subsequently,dynamic predictive models were constructed based on the Autoregressive Integrated Moving Average(ARIMA)and Long Short-Term Memory(LSTM)models.The hyperparameters of these models were optimized and selected using monitoring data from the immersed tunnel,yielding viable static and dynamic predictive models.Finally,the models were applied within the same segment of SHM data,to validate the effectiveness of the anomaly detection approach based on dynamic predictive modeling.A detailed comparative analysis discusses the discrepancies in temporal anomaly detection between the ARIMA-and LSTM-based models.The results demonstrated that the dynamic predictive modelbased anomaly detection approach was effective for dealing with unannotated SHM data.In a comparison between ARIMA and LSTM,it was found that ARIMA demonstrated higher modeling efficiency,rendering it suitable for short-term predictions.In contrast,the LSTM model exhibited greater capacity to capture long-term performance trends and enhanced early warning capabilities,thereby resulting in superior overall performance.展开更多
While emerging technologies such as the Internet of Things(IoT)have many benefits,they also pose considerable security challenges that require innovative solutions,including those based on artificial intelligence(AI),...While emerging technologies such as the Internet of Things(IoT)have many benefits,they also pose considerable security challenges that require innovative solutions,including those based on artificial intelligence(AI),given that these techniques are increasingly being used by malicious actors to compromise IoT systems.Although an ample body of research focusing on conventional AI methods exists,there is a paucity of studies related to advanced statistical and optimization approaches aimed at enhancing security measures.To contribute to this nascent research stream,a novel AI-driven security system denoted as“AI2AI”is presented in this work.AI2AI employs AI techniques to enhance the performance and optimize security mechanisms within the IoT framework.We also introduce the Genetic Algorithm Anomaly Detection and Prevention Deep Neural Networks(GAADPSDNN)sys-tem that can be implemented to effectively identify,detect,and prevent cyberattacks targeting IoT devices.Notably,this system demonstrates adaptability to both federated and centralized learning environments,accommodating a wide array of IoT devices.Our evaluation of the GAADPSDNN system using the recently complied WUSTL-IIoT and Edge-IIoT datasets underscores its efficacy.Achieving an impressive overall accuracy of 98.18%on the Edge-IIoT dataset,the GAADPSDNN outperforms the standard deep neural network(DNN)classifier with 94.11%accuracy.Furthermore,with the proposed enhancements,the accuracy of the unoptimized random forest classifier(80.89%)is improved to 93.51%,while the overall accuracy(98.18%)surpasses the results(93.91%,94.67%,94.94%,and 94.96%)achieved when alternative systems based on diverse optimization techniques and the same dataset are employed.The proposed optimization techniques increase the effectiveness of the anomaly detection system by efficiently achieving high accuracy and reducing the computational load on IoT devices through the adaptive selection of active features.展开更多
Internet of Things(IoT)is vulnerable to data-tampering(DT)attacks.Due to resource limitations,many anomaly detection systems(ADSs)for IoT have high false positive rates when detecting DT attacks.This leads to the misr...Internet of Things(IoT)is vulnerable to data-tampering(DT)attacks.Due to resource limitations,many anomaly detection systems(ADSs)for IoT have high false positive rates when detecting DT attacks.This leads to the misreporting of normal data,which will impact the normal operation of IoT.To mitigate the impact caused by the high false positive rate of ADS,this paper proposes an ADS management scheme for clustered IoT.First,we model the data transmission and anomaly detection in clustered IoT.Then,the operation strategy of the clustered IoT is formulated as the running probabilities of all ADSs deployed on every IoT device.In the presence of a high false positive rate in ADSs,to deal with the trade-off between the security and availability of data,we develop a linear programming model referred to as a security trade-off(ST)model.Next,we develop an analysis framework for the ST model,and solve the ST model on an IoT simulation platform.Last,we reveal the effect of some factors on the maximum combined detection rate through theoretical analysis.Simulations show that the ADS management scheme can mitigate the data unavailability loss caused by the high false positive rates in ADS.展开更多
Coronary artery anomaly is known as one of the causes of angina pectoris and sudden death and is an important clinical entity that cannot be overlooked.The incidence of coronary artery anomalies is as low as 1%-2%of t...Coronary artery anomaly is known as one of the causes of angina pectoris and sudden death and is an important clinical entity that cannot be overlooked.The incidence of coronary artery anomalies is as low as 1%-2%of the general population,even when the various types are combined.Coronary anomalies are practically challenging when the left and right coronary ostium are not found around their normal positions during coronary angiography with a catheter.If there is atherosclerotic stenosis of the coronary artery with an anomaly and percutaneous coronary intervention(PCI)is required,the suitability of the guiding catheter at the entrance and the adequate back up force of the guiding catheter are issues.The level of PCI risk itself should also be considered on a caseby-case basis.In this case,emission computed tomography in the R-1 subtype single coronary artery proved that ischemia occurred in an area where the coronary artery was not visible to the naked eye.Meticulous follow-up would be crucial,because sudden death may occur in single coronary arteries.To prevent atherosclerosis with full efforts is also important,as the authors indicated admirably.展开更多
Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series data.Due to the challenges associated with annotating anomaly events,time series reconst...Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series data.Due to the challenges associated with annotating anomaly events,time series reconstruction has become a prevalent approach for unsupervised anomaly detection.However,effectively learning representations and achieving accurate detection results remain challenging due to the intricate temporal patterns and dependencies in real-world time series.In this paper,we propose a cross-dimension attentive feature fusion network for time series anomaly detection,referred to as CAFFN.Specifically,a series and feature mixing block is introduced to learn representations in 1D space.Additionally,a fast Fourier transform is employed to convert the time series into 2D space,providing the capability for 2D feature extraction.Finally,a cross-dimension attentive feature fusion mechanism is designed that adaptively integrates features across different dimensions for anomaly detection.Experimental results on real-world time series datasets demonstrate that CAFFN performs better than other competing methods in time series anomaly detection.展开更多
The electron g-factor relates the magnetic moment to the spin angular momentum. It was originally theoretically calculated to have a value of exactly 2. Experiments yielded a value of 2 plus a very small fraction, ref...The electron g-factor relates the magnetic moment to the spin angular momentum. It was originally theoretically calculated to have a value of exactly 2. Experiments yielded a value of 2 plus a very small fraction, referred to as the g-factor anomaly. This anomaly has been calculated theoretically as a power series of the fine structure constant. This document shows that the anomaly is the result of the electron charge thickness. If the thickness were to be zero, g = 2 exactly, and there would be no anomaly. As the thickness increases, the anomaly increases. An equation relating the g-factor and the surface charge thickness is presented. The thickness is calculated to be 0.23% of the electron radius. The cause of the anomaly is very clear, but why is the charge thickness greater than zero? Using the model of the interior structure of the electron previously proposed by the author, it is shown that the non-zero thickness, and thus the g-factor anomaly, are due to the proposed positive charge at the electron center and compressibility of the electron material. The author’s previous publication proposes a theory for splitting the electron into three equal charges when subjected to a strong external magnetic field. That theory is revised in this document, and the result is an error reduced to 0.4% in the polar angle where the splits occur and a reduced magnetic field required to cause the splits.展开更多
The first part of this investigation analyzes the deep earthquake occurrences in Nazca subducting under South America. The depth taken is to get information about possible influences from the unknown materials and for...The first part of this investigation analyzes the deep earthquake occurrences in Nazca subducting under South America. The depth taken is to get information about possible influences from the unknown materials and formations under the crust. The results revealed the presence of malleable material, which is unbreakable and, therefore, unable to trigger earthquakes. The structure of those elements is diamagnetic, attracting ionized particles from the Van Allen belt region in the ionosphere. The charged particles travel towards Earth’s surface, enhanced during the geomagnetic storms. The South Atlantic Magnetic Anomaly (SAMA) found that the deformation suffered by the anomaly moving from South Africa to South America is, possibly due to a bulge of unknown flexible material buried underneath the oceanic and continental crust. The continental part is strengthening in weakness because the background also has a high amount of diamagnetic material in this region, and it would not happen over the Atlantic Ocean, where part of the deformation is placed.展开更多
This paper investigates the anomaly-resistant decentralized state estimation(SE) problem for a class of wide-area power systems which are divided into several non-overlapping areas connected through transmission lines...This paper investigates the anomaly-resistant decentralized state estimation(SE) problem for a class of wide-area power systems which are divided into several non-overlapping areas connected through transmission lines. Two classes of measurements(i.e., local measurements and edge measurements) are obtained, respectively, from the individual area and the transmission lines. A decentralized state estimator, whose performance is resistant against measurement with anomalies, is designed based on the minimum error entropy with fiducial points(MEEF) criterion. Specifically, 1) An augmented model, which incorporates the local prediction and local measurement, is developed by resorting to the unscented transformation approach and the statistical linearization approach;2) Using the augmented model, an MEEF-based cost function is designed that reflects the local prediction errors of the state and the measurement;and 3) The local estimate is first obtained by minimizing the MEEF-based cost function through a fixed-point iteration and then updated by using the edge measuring information. Finally, simulation experiments with three scenarios are carried out on the IEEE 14-bus system to illustrate the validity of the proposed anomaly-resistant decentralized SE scheme.展开更多
Accurate and effective identification of adverse geology is crucial for safe and efficient tunnel construction.Current methods of identifying adverse geology depend on the experience of geologists and are prone to mis...Accurate and effective identification of adverse geology is crucial for safe and efficient tunnel construction.Current methods of identifying adverse geology depend on the experience of geologists and are prone to misjudgment and omissions.Here,we propose a method for adverse geology identification in tunnels based on mineral anomaly analysis.The method is based on the theory of geoanomaly,and the mineral anomalies are geological markers of the presence of adverse geology.The method uses exploration data analysis(EDA)to calculate mineral anomaly thresholds,then evaluates the mineral anomalies based on the thresholds and identifies adverse geology based on the characteristics of the mineral anomalies.We have established a dynamic expansion process for background samples to achieve the dynamic evaluation of mineral anomalies by adjusting anomaly thresholds.This method has been validated and applied in a tunnel excavated in granite.As shown herein,in the tunnel range of 142+800–142+860,the fault F37 was successfully identified based on an anomalous decrease in the diagenetic minerals plagioclase and hornblende,as well as an anomalous increase in the content of the alteration minerals chlorite,laumonite,and epidote.The proposed method provides a timely warning when a tunnel enters areas affected by adverse geology and identifies whether the tunnel is gradually approaching or moving away from the fault.In addition,the applicability,accuracy,and further improvement of the method are discussed.This method improves our ability to identify adverse geology,from qualitative to quantitative,and can provide reference and guidance for the identification of adverse geology in mining and underground engineering.展开更多
With the extreme drought(flood)event in southern China from July to August in 2022(1999)as the research object,based on the comprehensive diagnosis and composite analysis on the anomalous drought and flood years from ...With the extreme drought(flood)event in southern China from July to August in 2022(1999)as the research object,based on the comprehensive diagnosis and composite analysis on the anomalous drought and flood years from July to August in 1961-2022,it is found that there are significant differences in the characteristics of the vertically integrated moisture flux(VIMF)anomaly circulation pattern and the VIMF convergence(VIMFC)anomaly in southern China in drought and flood years,and the VIMFC,a physical quantity,can be regarded as an indicative physical factor for the"strong signal"of drought and flood in southern China.Specifically,in drought years,the VIMF anomaly in southern China is an anticyclonic circulation pattern and the divergence characteristics of the VIMFC are prominent,while those are opposite in flood years.Based on the SST anomaly in the typical draught year of 2022 in southern China and the SST deviation distribution characteristics of abnormal draught and flood years from 1961 to 2022,five SST high impact areas(i.e.,the North Pacific Ocean,Northwest Pacific Ocean,Southwest Pacific Ocean,Indian Ocean,and East Pacific Ocean)are selected via the correlation analysis of VIMFC and the global SST in the preceding months(May and June)and in the study period(July and August)in 1961-2022,and their contributions to drought and flood in southern China are quantified.Our study reveals not only the persistent anomalous variation of SST in the Pacific and the Indian Ocean but also its impact on the pattern of moisture transport.Furthermore,it can be discovered from the positive and negative phase fitting of SST that the SST composite flow field in high impact areas can exhibit two types of anomalous moisture transport structures that are opposite to each other,namely an anticyclonic(cyclonic)circulation pattern anomaly in southern China and the coastal areas of east China.These two types of opposite anomalous moisture transport structures can not only drive the formation of drought(flood)in southern China but also exert its influence on the persistent development of the extreme weather.展开更多
Gravity Anomaly Correction(GAC)is a very important term in leveling data processing.In most cases,it is troublesome for field surveyors to measure gravity when leveling.In this paper,based on the complete Bouguer Grav...Gravity Anomaly Correction(GAC)is a very important term in leveling data processing.In most cases,it is troublesome for field surveyors to measure gravity when leveling.In this paper,based on the complete Bouguer Gravity Anomaly(BGA)map of WGM2012,the feasibility of replacing in-situ gravity surveying in China is investigated.For leveling application,that is to evaluate the accuracy of WGM2012 in China.Because WGM2012 is organized with a standard rectangle grid,two interpolation methods,bilinear interpolating and Inverse Distance Weighted(IDW)interpolating,are proposed.Four sample areas in China,i.e.,Hanzhong,Chengdu,Linzhi and Shantou,are selected to evaluate the systems bias and precision of WGM2012.Numerical results show the average system bias of WGM2012 BGA in west China is about-100.1 mGal(1 mGal=10^(-5) m/s^(2))and the standard deviation is about 30.7 mGal.Tests in Shantou indicate the system bias in plain areas is about-130.4 mGal and standard deviation is about 6.8 mGal.All these experiments means the accuracy of WGM2012 is limited in high mountain areas of western China,but in plain areas,such as Shantou,WGM2012 BGA map is quite good for most leveling applications after calibrating the system bias.展开更多
The evolution of the Internet of Things(IoT)has empowered modern industries with the capability to implement large-scale IoT ecosystems,such as the Industrial Internet of Things(IIoT).The IIoT is vulnerable to a diver...The evolution of the Internet of Things(IoT)has empowered modern industries with the capability to implement large-scale IoT ecosystems,such as the Industrial Internet of Things(IIoT).The IIoT is vulnerable to a diverse range of cyberattacks that can be exploited by intruders and cause substantial reputational andfinancial harm to organizations.To preserve the confidentiality,integrity,and availability of IIoT networks,an anomaly-based intrusion detection system(IDS)can be used to provide secure,reliable,and efficient IIoT ecosystems.In this paper,we propose an anomaly-based IDS for IIoT networks as an effective security solution to efficiently and effectively overcome several IIoT cyberattacks.The proposed anomaly-based IDS is divided into three phases:pre-processing,feature selection,and classification.In the pre-processing phase,data cleaning and nor-malization are performed.In the feature selection phase,the candidates’feature vectors are computed using two feature reduction techniques,minimum redun-dancy maximum relevance and neighborhood components analysis.For thefinal step,the modeling phase,the following classifiers are used to perform the classi-fication:support vector machine,decision tree,k-nearest neighbors,and linear discriminant analysis.The proposed work uses a new data-driven IIoT data set called X-IIoTID.The experimental evaluation demonstrates our proposed model achieved a high accuracy rate of 99.58%,a sensitivity rate of 99.59%,a specificity rate of 99.58%,and a low false positive rate of 0.4%.展开更多
Arctic changes influence not only temperature and precipitation in the midlatitudes but also contribute to severe convection.This study investigates an extreme gale event that occurred on 30 April 2021 in East China a...Arctic changes influence not only temperature and precipitation in the midlatitudes but also contribute to severe convection.This study investigates an extreme gale event that occurred on 30 April 2021 in East China and was forced by an Arctic potential vorticity(PV)anomaly intrusion.Temperature advection steered by storms contributed to the equatorward propagation of Arctic high PV,forming the Northeast China cold vortex(NCCV).At the upper levels,a PV southward intrusion guided the combination of the polar jet and the subtropical jet,providing strong vertical wind shear and downward momentum transportation to the event.The PV anomaly cooled the upper troposphere and the northern part of East China,whereas the lower levels over southern East China were dominated by local warm air,thus establishing strong instability and baroclinicity.In addition,the entrainment of Arctic dry air strengthened the surface pressure gradient by evaporation cooling.Capturing the above mechanism has the potential to improve convective weather forecasts under climate change.This study suggests that the more frequent NCCV-induced gale events in recent years are partly due to high-latitude waviness and storm activities,and this hypothesis needs to be investigated using more cases.展开更多
Log anomaly detection is an important paradigm for system troubleshooting.Existing log anomaly detection based on Long Short-Term Memory(LSTM)networks is time-consuming to handle long sequences.Transformer model is in...Log anomaly detection is an important paradigm for system troubleshooting.Existing log anomaly detection based on Long Short-Term Memory(LSTM)networks is time-consuming to handle long sequences.Transformer model is introduced to promote efficiency.However,most existing Transformer-based log anomaly detection methods convert unstructured log messages into structured templates by log parsing,which introduces parsing errors.They only extract simple semantic feature,which ignores other features,and are generally supervised,relying on the amount of labeled data.To overcome the limitations of existing methods,this paper proposes a novel unsupervised log anomaly detection method based on multi-feature(UMFLog).UMFLog includes two sub-models to consider two kinds of features:semantic feature and statistical feature,respectively.UMFLog applies the log original content with detailed parameters instead of templates or template IDs to avoid log parsing errors.In the first sub-model,UMFLog uses Bidirectional Encoder Representations from Transformers(BERT)instead of random initialization to extract effective semantic feature,and an unsupervised hypersphere-based Transformer model to learn compact log sequence representations and obtain anomaly candidates.In the second sub-model,UMFLog exploits a statistical feature-based Variational Autoencoder(VAE)about word occurrence times to identify the final anomaly from anomaly candidates.Extensive experiments and evaluations are conducted on three real public log datasets.The results show that UMFLog significantly improves F1-scores compared to the state-of-the-art(SOTA)methods because of the multi-feature.展开更多
Solar arrays are important and indispensable parts of spacecraft and provide energy support for spacecraft to operate in orbit and complete on-orbit missions.When a spacecraft is in orbit,because the solar array is ex...Solar arrays are important and indispensable parts of spacecraft and provide energy support for spacecraft to operate in orbit and complete on-orbit missions.When a spacecraft is in orbit,because the solar array is exposed to the harsh space environment,with increasing working time,the performance of its internal electronic components gradually degrade until abnormal damage occurs.This damage makes solar array power generation unable to fully meet the energy demand of a spacecraft.Therefore,timely and accurate detection of solar array anomalies is of great significance for the on-orbit operation and maintenance management of spacecraft.In this paper,we propose an anomaly detection method for spacecraft solar arrays based on the integrated least squares support vector machine(ILS-SVM)model:it selects correlated telemetry data from spacecraft solar arrays to form a training set and extracts n groups of training subsets from this set,then gets n corresponding least squares support vector machine(LS-SVM)submodels by training on these training subsets,respectively;after that,the ILS-SVM model is obtained by integrating these submodels through a weighting operation to increase the prediction accuracy and so on;finally,based on the obtained ILS-SVM model,a parameterfree and unsupervised anomaly determination method is proposed to detect the health status of solar arrays.We use the telemetry data set from a satellite in orbit to carry out experimental verification and find that the proposed method can diagnose solar array anomalies in time and can capture the signs before a solar array anomaly occurs,which reflects the applicability of the method.展开更多
The South Atlantic Anomaly(SAA)is a region where the geomagnetic field is significantly lower than that of the surrounding area.On the basis of the models of CHAOS-7.8,Mass Spectrometer Incoherent Scatter Model(NRLMSI...The South Atlantic Anomaly(SAA)is a region where the geomagnetic field is significantly lower than that of the surrounding area.On the basis of the models of CHAOS-7.8,Mass Spectrometer Incoherent Scatter Model(NRLMSISE-00),and International Reference Ionosphere 2016(IRI-2016),we theoretically investigated the lower and upper boundaries of the ionospheric dynamo region inside the SAA.In the ionospheric dynamo region,electrons are coupled with magnetic field lines,whereas ions are decoupled from magnetic field lines.Our results showed that the ionospheric dynamo region inside the SAA is higher and larger than that outside the SAA.We also studied the boundary variations of the dynamo region inside the SAA depending on the seasons and solar activities.We found that the dynamo region inside the SAA is the highest and largest in the summer of the southern hemisphere at solar maximum.The larger and higher altitude range of the ionospheric dynamo region in the SAA can contribute to the stronger ionospheric currents in this region.展开更多
The Cloud system shows its growing functionalities in various industrial applications.The safety towards data transfer seems to be a threat where Network Intrusion Detection System(NIDS)is measured as an essential ele...The Cloud system shows its growing functionalities in various industrial applications.The safety towards data transfer seems to be a threat where Network Intrusion Detection System(NIDS)is measured as an essential element to fulfill security.Recently,Machine Learning(ML)approaches have been used for the construction of intellectual IDS.Most IDS are based on ML techniques either as unsupervised or supervised.In supervised learning,NIDS is based on labeled data where it reduces the efficiency of the reduced model to identify attack patterns.Similarly,the unsupervised model fails to provide a satisfactory outcome.Hence,to boost the functionality of unsupervised learning,an effectual auto-encoder is applied for feature selection to select good features.Finally,the Naïve Bayes classifier is used for classification purposes.This approach exposes the finest generalization ability to train the data.The unlabelled data is also used for adoption towards data analysis.Here,redundant and noisy samples over the dataset are eliminated.To validate the robustness and efficiency of NIDS,the anticipated model is tested over the NSL-KDD dataset.The experimental outcomes demonstrate that the anticipated approach attains superior accuracy with 93%,which is higher compared to J48,AB tree,Random Forest(RF),Regression Tree(RT),Multi-Layer Perceptrons(MLP),Support Vector Machine(SVM),and Fuzzy.Similarly,False Alarm Rate(FAR)and True Positive Rate(TPR)of Naive Bayes(NB)is 0.3 and 0.99,respectively.When compared to prevailing techniques,the anticipated approach also delivers promising outcomes.展开更多
Despite the big success of transfer learning techniques in anomaly detection,it is still challenging to achieve good transition of detection rules merely based on the preferred data in the anomaly detection with one-c...Despite the big success of transfer learning techniques in anomaly detection,it is still challenging to achieve good transition of detection rules merely based on the preferred data in the anomaly detection with one-class classification,especially for the data with a large distribution difference.To address this challenge,a novel deep one-class transfer learning algorithm with domain-adversarial training is proposed in this paper.First,by integrating a hypersphere adaptation constraint into domainadversarial neural network,a new hypersphere adversarial training mechanism is designed.Second,an alternative optimization method is derived to seek the optimal network parameters while pushing the hyperspheres built in the source domain and target domain to be as identical as possible.Through transferring oneclass detection rule in the adaptive extraction of domain-invariant feature representation,the end-to-end anomaly detection with one-class classification is then enhanced.Furthermore,a theoretical analysis about the model reliability,as well as the strategy of avoiding invalid and negative transfer,is provided.Experiments are conducted on two typical anomaly detection problems,i.e.,image recognition detection and online early fault detection of rolling bearings.The results demonstrate that the proposed algorithm outperforms the state-of-the-art methods in terms of detection accuracy and robustness.展开更多
Rationale: Pompholyx refers to pruritic vesicles or bullous rash that mainly distribute on the palms and lateral surfaces of the fingers. It is less common among Asians, and in a severe condition, secondary bacterial ...Rationale: Pompholyx refers to pruritic vesicles or bullous rash that mainly distribute on the palms and lateral surfaces of the fingers. It is less common among Asians, and in a severe condition, secondary bacterial infection of pompholyx can happen and result in pain, swelling and pustules.Patient concerns: A 15-year-old girl complained of progressive wound and small bumps containing yellowish pus and crusts on her hands and feet for over 6 months and worsened in the last month before admission. She also had Ebstein anomaly.Diagnosis: Atypical pompholyx with secondary Staphylococcus and Klebsiella infections. Interventions: Wound care with wet dressing and applying moisturizer on crusts, application of antibiotics for Gram positive and negative bacteria and giving nutritional support with reckoning of proper calories. Outcomes: Skin lesions were completely healed and the patient was discharged after 10 days of hospitalization.Lessons: Atypical manifestation of pompholyx makes it hard to diagnose. The diagnosis can be confirmed with meticulous historytaking and physical examination. Wound caring and controlling of the infection should be done to earn an optimal outcome.展开更多
Research on strain anomalies and large earthquakes based on temporal and spatial crustal activities has been rapidly growing due to data availability, especially in Japan and Indonesia. However, many research works us...Research on strain anomalies and large earthquakes based on temporal and spatial crustal activities has been rapidly growing due to data availability, especially in Japan and Indonesia. However, many research works used local-scale case studies that focused on a specific earthquake characteristic using knowledgedriven techniques, such as crustal deformation analysis. In this study, a data-driven-based analysis is used to detect anomalies using displacement rates and deformation pattern features extracted from daily global navigation satellite system(GNSS) data using a machine learning algorithm. The GNSS data with188 and 1181 continuously operating reference stations from Indonesia and Japan, respectively, are used to identify the anomaly of recent major earthquakes in the last two decades. Feature displacement rates and deformation patterns are processed in several window times with 2560 experiment scenarios to produce the best detection using tree-based algorithms. Tree-based algorithms with a single estimator(decision tree), ensemble bagging(bagging, random forest and Extra Trees), and ensemble boosting(AdaBoost, gradient boosting, LGBM, and XGB) are applied in the study. The experiment test using realtime scenario GNSSdailydatareveals high F1-scores and accuracy for anomaly detection using slope windowing 365 and 730 days of 91-day displacement rates and then 7-day deformation pattern features in tree-based algorithms. The results show the potential for medium-term anomaly detection using GNSS data without the need for multiple vulnerability assessments.展开更多
基金supported by the Research and Development Center of Transport Industry of New Generation of Artificial Intelligence Technology(Grant No.202202H)the National Key R&D Program of China(Grant No.2019YFB1600702)the National Natural Science Foundation of China(Grant Nos.51978600&51808336).
文摘Structural Health Monitoring(SHM)systems have become a crucial tool for the operational management of long tunnels.For immersed tunnels exposed to both traffic loads and the effects of the marine environment,efficiently identifying abnormal conditions from the extensive unannotated SHM data presents a significant challenge.This study proposed amodel-based approach for anomaly detection and conducted validation and comparative analysis of two distinct temporal predictive models using SHM data from a real immersed tunnel.Firstly,a dynamic predictive model-based anomaly detectionmethod is proposed,which utilizes a rolling time window for modeling to achieve dynamic prediction.Leveraging the assumption of temporal data similarity,an interval prediction value deviation was employed to determine the abnormality of the data.Subsequently,dynamic predictive models were constructed based on the Autoregressive Integrated Moving Average(ARIMA)and Long Short-Term Memory(LSTM)models.The hyperparameters of these models were optimized and selected using monitoring data from the immersed tunnel,yielding viable static and dynamic predictive models.Finally,the models were applied within the same segment of SHM data,to validate the effectiveness of the anomaly detection approach based on dynamic predictive modeling.A detailed comparative analysis discusses the discrepancies in temporal anomaly detection between the ARIMA-and LSTM-based models.The results demonstrated that the dynamic predictive modelbased anomaly detection approach was effective for dealing with unannotated SHM data.In a comparison between ARIMA and LSTM,it was found that ARIMA demonstrated higher modeling efficiency,rendering it suitable for short-term predictions.In contrast,the LSTM model exhibited greater capacity to capture long-term performance trends and enhanced early warning capabilities,thereby resulting in superior overall performance.
文摘While emerging technologies such as the Internet of Things(IoT)have many benefits,they also pose considerable security challenges that require innovative solutions,including those based on artificial intelligence(AI),given that these techniques are increasingly being used by malicious actors to compromise IoT systems.Although an ample body of research focusing on conventional AI methods exists,there is a paucity of studies related to advanced statistical and optimization approaches aimed at enhancing security measures.To contribute to this nascent research stream,a novel AI-driven security system denoted as“AI2AI”is presented in this work.AI2AI employs AI techniques to enhance the performance and optimize security mechanisms within the IoT framework.We also introduce the Genetic Algorithm Anomaly Detection and Prevention Deep Neural Networks(GAADPSDNN)sys-tem that can be implemented to effectively identify,detect,and prevent cyberattacks targeting IoT devices.Notably,this system demonstrates adaptability to both federated and centralized learning environments,accommodating a wide array of IoT devices.Our evaluation of the GAADPSDNN system using the recently complied WUSTL-IIoT and Edge-IIoT datasets underscores its efficacy.Achieving an impressive overall accuracy of 98.18%on the Edge-IIoT dataset,the GAADPSDNN outperforms the standard deep neural network(DNN)classifier with 94.11%accuracy.Furthermore,with the proposed enhancements,the accuracy of the unoptimized random forest classifier(80.89%)is improved to 93.51%,while the overall accuracy(98.18%)surpasses the results(93.91%,94.67%,94.94%,and 94.96%)achieved when alternative systems based on diverse optimization techniques and the same dataset are employed.The proposed optimization techniques increase the effectiveness of the anomaly detection system by efficiently achieving high accuracy and reducing the computational load on IoT devices through the adaptive selection of active features.
基金This study was funded by the Chongqing Normal University Startup Foundation for PhD(22XLB021)was also supported by the Open Research Project of the State Key Laboratory of Industrial Control Technology,Zhejiang University,China(No.ICT2023B40).
文摘Internet of Things(IoT)is vulnerable to data-tampering(DT)attacks.Due to resource limitations,many anomaly detection systems(ADSs)for IoT have high false positive rates when detecting DT attacks.This leads to the misreporting of normal data,which will impact the normal operation of IoT.To mitigate the impact caused by the high false positive rate of ADS,this paper proposes an ADS management scheme for clustered IoT.First,we model the data transmission and anomaly detection in clustered IoT.Then,the operation strategy of the clustered IoT is formulated as the running probabilities of all ADSs deployed on every IoT device.In the presence of a high false positive rate in ADSs,to deal with the trade-off between the security and availability of data,we develop a linear programming model referred to as a security trade-off(ST)model.Next,we develop an analysis framework for the ST model,and solve the ST model on an IoT simulation platform.Last,we reveal the effect of some factors on the maximum combined detection rate through theoretical analysis.Simulations show that the ADS management scheme can mitigate the data unavailability loss caused by the high false positive rates in ADS.
文摘Coronary artery anomaly is known as one of the causes of angina pectoris and sudden death and is an important clinical entity that cannot be overlooked.The incidence of coronary artery anomalies is as low as 1%-2%of the general population,even when the various types are combined.Coronary anomalies are practically challenging when the left and right coronary ostium are not found around their normal positions during coronary angiography with a catheter.If there is atherosclerotic stenosis of the coronary artery with an anomaly and percutaneous coronary intervention(PCI)is required,the suitability of the guiding catheter at the entrance and the adequate back up force of the guiding catheter are issues.The level of PCI risk itself should also be considered on a caseby-case basis.In this case,emission computed tomography in the R-1 subtype single coronary artery proved that ischemia occurred in an area where the coronary artery was not visible to the naked eye.Meticulous follow-up would be crucial,because sudden death may occur in single coronary arteries.To prevent atherosclerosis with full efforts is also important,as the authors indicated admirably.
基金supported in part by the National Natural Science Foundation of China(Grants 62376172,62006163,62376043)in part by the National Postdoctoral Program for Innovative Talents(Grant BX20200226)in part by Sichuan Science and Technology Planning Project(Grants 2022YFSY0047,2022YFQ0014,2023ZYD0143,2022YFH0021,2023YFQ0020,24QYCX0354,24NSFTD0025).
文摘Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series data.Due to the challenges associated with annotating anomaly events,time series reconstruction has become a prevalent approach for unsupervised anomaly detection.However,effectively learning representations and achieving accurate detection results remain challenging due to the intricate temporal patterns and dependencies in real-world time series.In this paper,we propose a cross-dimension attentive feature fusion network for time series anomaly detection,referred to as CAFFN.Specifically,a series and feature mixing block is introduced to learn representations in 1D space.Additionally,a fast Fourier transform is employed to convert the time series into 2D space,providing the capability for 2D feature extraction.Finally,a cross-dimension attentive feature fusion mechanism is designed that adaptively integrates features across different dimensions for anomaly detection.Experimental results on real-world time series datasets demonstrate that CAFFN performs better than other competing methods in time series anomaly detection.
文摘The electron g-factor relates the magnetic moment to the spin angular momentum. It was originally theoretically calculated to have a value of exactly 2. Experiments yielded a value of 2 plus a very small fraction, referred to as the g-factor anomaly. This anomaly has been calculated theoretically as a power series of the fine structure constant. This document shows that the anomaly is the result of the electron charge thickness. If the thickness were to be zero, g = 2 exactly, and there would be no anomaly. As the thickness increases, the anomaly increases. An equation relating the g-factor and the surface charge thickness is presented. The thickness is calculated to be 0.23% of the electron radius. The cause of the anomaly is very clear, but why is the charge thickness greater than zero? Using the model of the interior structure of the electron previously proposed by the author, it is shown that the non-zero thickness, and thus the g-factor anomaly, are due to the proposed positive charge at the electron center and compressibility of the electron material. The author’s previous publication proposes a theory for splitting the electron into three equal charges when subjected to a strong external magnetic field. That theory is revised in this document, and the result is an error reduced to 0.4% in the polar angle where the splits occur and a reduced magnetic field required to cause the splits.
文摘The first part of this investigation analyzes the deep earthquake occurrences in Nazca subducting under South America. The depth taken is to get information about possible influences from the unknown materials and formations under the crust. The results revealed the presence of malleable material, which is unbreakable and, therefore, unable to trigger earthquakes. The structure of those elements is diamagnetic, attracting ionized particles from the Van Allen belt region in the ionosphere. The charged particles travel towards Earth’s surface, enhanced during the geomagnetic storms. The South Atlantic Magnetic Anomaly (SAMA) found that the deformation suffered by the anomaly moving from South Africa to South America is, possibly due to a bulge of unknown flexible material buried underneath the oceanic and continental crust. The continental part is strengthening in weakness because the background also has a high amount of diamagnetic material in this region, and it would not happen over the Atlantic Ocean, where part of the deformation is placed.
基金supported in part by the National Natural Science Foundation of China(61933007, U21A2019, 62273005, 62273088, 62303301)the Program of Shanghai Academic/Technology Research Leader of China (20XD1420100)+2 种基金the Hainan Province Science and Technology Special Fund of China(ZDYF2022SHFZ105)the Natural Science Foundation of Anhui Province of China (2108085MA07)the Alexander von Humboldt Foundation of Germany。
文摘This paper investigates the anomaly-resistant decentralized state estimation(SE) problem for a class of wide-area power systems which are divided into several non-overlapping areas connected through transmission lines. Two classes of measurements(i.e., local measurements and edge measurements) are obtained, respectively, from the individual area and the transmission lines. A decentralized state estimator, whose performance is resistant against measurement with anomalies, is designed based on the minimum error entropy with fiducial points(MEEF) criterion. Specifically, 1) An augmented model, which incorporates the local prediction and local measurement, is developed by resorting to the unscented transformation approach and the statistical linearization approach;2) Using the augmented model, an MEEF-based cost function is designed that reflects the local prediction errors of the state and the measurement;and 3) The local estimate is first obtained by minimizing the MEEF-based cost function through a fixed-point iteration and then updated by using the edge measuring information. Finally, simulation experiments with three scenarios are carried out on the IEEE 14-bus system to illustrate the validity of the proposed anomaly-resistant decentralized SE scheme.
基金financial support from the National Natural Science Foundation of China(52022053 and 52009073)the Natural Science Foundation of Shandong Province(ZR201910270116)。
文摘Accurate and effective identification of adverse geology is crucial for safe and efficient tunnel construction.Current methods of identifying adverse geology depend on the experience of geologists and are prone to misjudgment and omissions.Here,we propose a method for adverse geology identification in tunnels based on mineral anomaly analysis.The method is based on the theory of geoanomaly,and the mineral anomalies are geological markers of the presence of adverse geology.The method uses exploration data analysis(EDA)to calculate mineral anomaly thresholds,then evaluates the mineral anomalies based on the thresholds and identifies adverse geology based on the characteristics of the mineral anomalies.We have established a dynamic expansion process for background samples to achieve the dynamic evaluation of mineral anomalies by adjusting anomaly thresholds.This method has been validated and applied in a tunnel excavated in granite.As shown herein,in the tunnel range of 142+800–142+860,the fault F37 was successfully identified based on an anomalous decrease in the diagenetic minerals plagioclase and hornblende,as well as an anomalous increase in the content of the alteration minerals chlorite,laumonite,and epidote.The proposed method provides a timely warning when a tunnel enters areas affected by adverse geology and identifies whether the tunnel is gradually approaching or moving away from the fault.In addition,the applicability,accuracy,and further improvement of the method are discussed.This method improves our ability to identify adverse geology,from qualitative to quantitative,and can provide reference and guidance for the identification of adverse geology in mining and underground engineering.
基金The Second Tibetan Plateau Scientific Expedition and Research(STEP)Program(2019QZKK0105)the Science and Technology Development Fund of the Chinese Academy of Meteorological Sciences(2022KJ022)+2 种基金Special Fund for the Basic Scientific Research Expenses of the Chinese Academy of Meteorological Sciences(2021Z013)the Science and Technology Development Fund of the Chinese Academy of Meteorological Sciences(2022KJ021)Major Projects of the Natural Science Foundation of China(91337000)。
文摘With the extreme drought(flood)event in southern China from July to August in 2022(1999)as the research object,based on the comprehensive diagnosis and composite analysis on the anomalous drought and flood years from July to August in 1961-2022,it is found that there are significant differences in the characteristics of the vertically integrated moisture flux(VIMF)anomaly circulation pattern and the VIMF convergence(VIMFC)anomaly in southern China in drought and flood years,and the VIMFC,a physical quantity,can be regarded as an indicative physical factor for the"strong signal"of drought and flood in southern China.Specifically,in drought years,the VIMF anomaly in southern China is an anticyclonic circulation pattern and the divergence characteristics of the VIMFC are prominent,while those are opposite in flood years.Based on the SST anomaly in the typical draught year of 2022 in southern China and the SST deviation distribution characteristics of abnormal draught and flood years from 1961 to 2022,five SST high impact areas(i.e.,the North Pacific Ocean,Northwest Pacific Ocean,Southwest Pacific Ocean,Indian Ocean,and East Pacific Ocean)are selected via the correlation analysis of VIMFC and the global SST in the preceding months(May and June)and in the study period(July and August)in 1961-2022,and their contributions to drought and flood in southern China are quantified.Our study reveals not only the persistent anomalous variation of SST in the Pacific and the Indian Ocean but also its impact on the pattern of moisture transport.Furthermore,it can be discovered from the positive and negative phase fitting of SST that the SST composite flow field in high impact areas can exhibit two types of anomalous moisture transport structures that are opposite to each other,namely an anticyclonic(cyclonic)circulation pattern anomaly in southern China and the coastal areas of east China.These two types of opposite anomalous moisture transport structures can not only drive the formation of drought(flood)in southern China but also exert its influence on the persistent development of the extreme weather.
基金“Wings of Quality”Program of QICS(No.2020-zlzy-015)。
文摘Gravity Anomaly Correction(GAC)is a very important term in leveling data processing.In most cases,it is troublesome for field surveyors to measure gravity when leveling.In this paper,based on the complete Bouguer Gravity Anomaly(BGA)map of WGM2012,the feasibility of replacing in-situ gravity surveying in China is investigated.For leveling application,that is to evaluate the accuracy of WGM2012 in China.Because WGM2012 is organized with a standard rectangle grid,two interpolation methods,bilinear interpolating and Inverse Distance Weighted(IDW)interpolating,are proposed.Four sample areas in China,i.e.,Hanzhong,Chengdu,Linzhi and Shantou,are selected to evaluate the systems bias and precision of WGM2012.Numerical results show the average system bias of WGM2012 BGA in west China is about-100.1 mGal(1 mGal=10^(-5) m/s^(2))and the standard deviation is about 30.7 mGal.Tests in Shantou indicate the system bias in plain areas is about-130.4 mGal and standard deviation is about 6.8 mGal.All these experiments means the accuracy of WGM2012 is limited in high mountain areas of western China,but in plain areas,such as Shantou,WGM2012 BGA map is quite good for most leveling applications after calibrating the system bias.
文摘The evolution of the Internet of Things(IoT)has empowered modern industries with the capability to implement large-scale IoT ecosystems,such as the Industrial Internet of Things(IIoT).The IIoT is vulnerable to a diverse range of cyberattacks that can be exploited by intruders and cause substantial reputational andfinancial harm to organizations.To preserve the confidentiality,integrity,and availability of IIoT networks,an anomaly-based intrusion detection system(IDS)can be used to provide secure,reliable,and efficient IIoT ecosystems.In this paper,we propose an anomaly-based IDS for IIoT networks as an effective security solution to efficiently and effectively overcome several IIoT cyberattacks.The proposed anomaly-based IDS is divided into three phases:pre-processing,feature selection,and classification.In the pre-processing phase,data cleaning and nor-malization are performed.In the feature selection phase,the candidates’feature vectors are computed using two feature reduction techniques,minimum redun-dancy maximum relevance and neighborhood components analysis.For thefinal step,the modeling phase,the following classifiers are used to perform the classi-fication:support vector machine,decision tree,k-nearest neighbors,and linear discriminant analysis.The proposed work uses a new data-driven IIoT data set called X-IIoTID.The experimental evaluation demonstrates our proposed model achieved a high accuracy rate of 99.58%,a sensitivity rate of 99.59%,a specificity rate of 99.58%,and a low false positive rate of 0.4%.
基金supported by the China National Science Foundation (Grant No. 41705029)Anhui Joint Foundation (Grant No.2208085UQ11)+2 种基金China Meteorological Administration special grants on innovation and development (Grant No. CXFZ2023J017)China Meteorological Administration special grants on decision-making meteorological service (Grant No. JCZX2022005)support from the innovation team at Anhui Meteorological Bureau
文摘Arctic changes influence not only temperature and precipitation in the midlatitudes but also contribute to severe convection.This study investigates an extreme gale event that occurred on 30 April 2021 in East China and was forced by an Arctic potential vorticity(PV)anomaly intrusion.Temperature advection steered by storms contributed to the equatorward propagation of Arctic high PV,forming the Northeast China cold vortex(NCCV).At the upper levels,a PV southward intrusion guided the combination of the polar jet and the subtropical jet,providing strong vertical wind shear and downward momentum transportation to the event.The PV anomaly cooled the upper troposphere and the northern part of East China,whereas the lower levels over southern East China were dominated by local warm air,thus establishing strong instability and baroclinicity.In addition,the entrainment of Arctic dry air strengthened the surface pressure gradient by evaporation cooling.Capturing the above mechanism has the potential to improve convective weather forecasts under climate change.This study suggests that the more frequent NCCV-induced gale events in recent years are partly due to high-latitude waviness and storm activities,and this hypothesis needs to be investigated using more cases.
基金supported in part by the National Natural Science Foundation of China under Grant 62272062the Scientific Research Fund of Hunan Provincial Transportation Department(No.202143)the Open Fund ofKey Laboratory of Safety Control of Bridge Engineering,Ministry of Education(Changsha University of Science Technology)under Grant 21KB07.
文摘Log anomaly detection is an important paradigm for system troubleshooting.Existing log anomaly detection based on Long Short-Term Memory(LSTM)networks is time-consuming to handle long sequences.Transformer model is introduced to promote efficiency.However,most existing Transformer-based log anomaly detection methods convert unstructured log messages into structured templates by log parsing,which introduces parsing errors.They only extract simple semantic feature,which ignores other features,and are generally supervised,relying on the amount of labeled data.To overcome the limitations of existing methods,this paper proposes a novel unsupervised log anomaly detection method based on multi-feature(UMFLog).UMFLog includes two sub-models to consider two kinds of features:semantic feature and statistical feature,respectively.UMFLog applies the log original content with detailed parameters instead of templates or template IDs to avoid log parsing errors.In the first sub-model,UMFLog uses Bidirectional Encoder Representations from Transformers(BERT)instead of random initialization to extract effective semantic feature,and an unsupervised hypersphere-based Transformer model to learn compact log sequence representations and obtain anomaly candidates.In the second sub-model,UMFLog exploits a statistical feature-based Variational Autoencoder(VAE)about word occurrence times to identify the final anomaly from anomaly candidates.Extensive experiments and evaluations are conducted on three real public log datasets.The results show that UMFLog significantly improves F1-scores compared to the state-of-the-art(SOTA)methods because of the multi-feature.
基金supported by the National Natural Science Foundation of China(7190121061973310).
文摘Solar arrays are important and indispensable parts of spacecraft and provide energy support for spacecraft to operate in orbit and complete on-orbit missions.When a spacecraft is in orbit,because the solar array is exposed to the harsh space environment,with increasing working time,the performance of its internal electronic components gradually degrade until abnormal damage occurs.This damage makes solar array power generation unable to fully meet the energy demand of a spacecraft.Therefore,timely and accurate detection of solar array anomalies is of great significance for the on-orbit operation and maintenance management of spacecraft.In this paper,we propose an anomaly detection method for spacecraft solar arrays based on the integrated least squares support vector machine(ILS-SVM)model:it selects correlated telemetry data from spacecraft solar arrays to form a training set and extracts n groups of training subsets from this set,then gets n corresponding least squares support vector machine(LS-SVM)submodels by training on these training subsets,respectively;after that,the ILS-SVM model is obtained by integrating these submodels through a weighting operation to increase the prediction accuracy and so on;finally,based on the obtained ILS-SVM model,a parameterfree and unsupervised anomaly determination method is proposed to detect the health status of solar arrays.We use the telemetry data set from a satellite in orbit to carry out experimental verification and find that the proposed method can diagnose solar array anomalies in time and can capture the signs before a solar array anomaly occurs,which reflects the applicability of the method.
基金supported by the National Natural Science Foundation of China(undergrant no.42122061)Macao Foundation+1 种基金the Project of Civil Aerospace“13th Five Year Plan”Preliminary Research in Space Science(grant nos.D020308 and D020301)the international partnership program of the Chinese Academy of Sciences(grant no.183311KYSB20200017)。
文摘The South Atlantic Anomaly(SAA)is a region where the geomagnetic field is significantly lower than that of the surrounding area.On the basis of the models of CHAOS-7.8,Mass Spectrometer Incoherent Scatter Model(NRLMSISE-00),and International Reference Ionosphere 2016(IRI-2016),we theoretically investigated the lower and upper boundaries of the ionospheric dynamo region inside the SAA.In the ionospheric dynamo region,electrons are coupled with magnetic field lines,whereas ions are decoupled from magnetic field lines.Our results showed that the ionospheric dynamo region inside the SAA is higher and larger than that outside the SAA.We also studied the boundary variations of the dynamo region inside the SAA depending on the seasons and solar activities.We found that the dynamo region inside the SAA is the highest and largest in the summer of the southern hemisphere at solar maximum.The larger and higher altitude range of the ionospheric dynamo region in the SAA can contribute to the stronger ionospheric currents in this region.
文摘The Cloud system shows its growing functionalities in various industrial applications.The safety towards data transfer seems to be a threat where Network Intrusion Detection System(NIDS)is measured as an essential element to fulfill security.Recently,Machine Learning(ML)approaches have been used for the construction of intellectual IDS.Most IDS are based on ML techniques either as unsupervised or supervised.In supervised learning,NIDS is based on labeled data where it reduces the efficiency of the reduced model to identify attack patterns.Similarly,the unsupervised model fails to provide a satisfactory outcome.Hence,to boost the functionality of unsupervised learning,an effectual auto-encoder is applied for feature selection to select good features.Finally,the Naïve Bayes classifier is used for classification purposes.This approach exposes the finest generalization ability to train the data.The unlabelled data is also used for adoption towards data analysis.Here,redundant and noisy samples over the dataset are eliminated.To validate the robustness and efficiency of NIDS,the anticipated model is tested over the NSL-KDD dataset.The experimental outcomes demonstrate that the anticipated approach attains superior accuracy with 93%,which is higher compared to J48,AB tree,Random Forest(RF),Regression Tree(RT),Multi-Layer Perceptrons(MLP),Support Vector Machine(SVM),and Fuzzy.Similarly,False Alarm Rate(FAR)and True Positive Rate(TPR)of Naive Bayes(NB)is 0.3 and 0.99,respectively.When compared to prevailing techniques,the anticipated approach also delivers promising outcomes.
基金supported by the National Natural Science Foundation of China(NSFC)(U1704158)Henan Province Technologies Research and Development Project of China(212102210103)+1 种基金the NSFC Development Funding of Henan Normal University(2020PL09)the University of Manitoba Research Grants Program(URGP)。
文摘Despite the big success of transfer learning techniques in anomaly detection,it is still challenging to achieve good transition of detection rules merely based on the preferred data in the anomaly detection with one-class classification,especially for the data with a large distribution difference.To address this challenge,a novel deep one-class transfer learning algorithm with domain-adversarial training is proposed in this paper.First,by integrating a hypersphere adaptation constraint into domainadversarial neural network,a new hypersphere adversarial training mechanism is designed.Second,an alternative optimization method is derived to seek the optimal network parameters while pushing the hyperspheres built in the source domain and target domain to be as identical as possible.Through transferring oneclass detection rule in the adaptive extraction of domain-invariant feature representation,the end-to-end anomaly detection with one-class classification is then enhanced.Furthermore,a theoretical analysis about the model reliability,as well as the strategy of avoiding invalid and negative transfer,is provided.Experiments are conducted on two typical anomaly detection problems,i.e.,image recognition detection and online early fault detection of rolling bearings.The results demonstrate that the proposed algorithm outperforms the state-of-the-art methods in terms of detection accuracy and robustness.
文摘Rationale: Pompholyx refers to pruritic vesicles or bullous rash that mainly distribute on the palms and lateral surfaces of the fingers. It is less common among Asians, and in a severe condition, secondary bacterial infection of pompholyx can happen and result in pain, swelling and pustules.Patient concerns: A 15-year-old girl complained of progressive wound and small bumps containing yellowish pus and crusts on her hands and feet for over 6 months and worsened in the last month before admission. She also had Ebstein anomaly.Diagnosis: Atypical pompholyx with secondary Staphylococcus and Klebsiella infections. Interventions: Wound care with wet dressing and applying moisturizer on crusts, application of antibiotics for Gram positive and negative bacteria and giving nutritional support with reckoning of proper calories. Outcomes: Skin lesions were completely healed and the patient was discharged after 10 days of hospitalization.Lessons: Atypical manifestation of pompholyx makes it hard to diagnose. The diagnosis can be confirmed with meticulous historytaking and physical examination. Wound caring and controlling of the infection should be done to earn an optimal outcome.
基金the Program PenelitianKolaborasi Indonesia(PPKI)Non APBN Universitas Diponegoro Universitas Diponegoro Indonesia under Grant 117-03/UN7.6.1/PP/2021.
文摘Research on strain anomalies and large earthquakes based on temporal and spatial crustal activities has been rapidly growing due to data availability, especially in Japan and Indonesia. However, many research works used local-scale case studies that focused on a specific earthquake characteristic using knowledgedriven techniques, such as crustal deformation analysis. In this study, a data-driven-based analysis is used to detect anomalies using displacement rates and deformation pattern features extracted from daily global navigation satellite system(GNSS) data using a machine learning algorithm. The GNSS data with188 and 1181 continuously operating reference stations from Indonesia and Japan, respectively, are used to identify the anomaly of recent major earthquakes in the last two decades. Feature displacement rates and deformation patterns are processed in several window times with 2560 experiment scenarios to produce the best detection using tree-based algorithms. Tree-based algorithms with a single estimator(decision tree), ensemble bagging(bagging, random forest and Extra Trees), and ensemble boosting(AdaBoost, gradient boosting, LGBM, and XGB) are applied in the study. The experiment test using realtime scenario GNSSdailydatareveals high F1-scores and accuracy for anomaly detection using slope windowing 365 and 730 days of 91-day displacement rates and then 7-day deformation pattern features in tree-based algorithms. The results show the potential for medium-term anomaly detection using GNSS data without the need for multiple vulnerability assessments.