As cloud system architectures evolve continuously,the interac-tions among distributed components in various roles become increasingly complex.This complexity makes it difficult to detect anomalies in cloud systems.The...As cloud system architectures evolve continuously,the interac-tions among distributed components in various roles become increasingly complex.This complexity makes it difficult to detect anomalies in cloud systems.The system status can no longer be determined through individual key performance indicators(KPIs)but through joint judgments based on syn-ergistic relationships among distributed components.Furthermore,anomalies in modern cloud systems are usually not sudden crashes but rather grad-ual,chronic,localized failures or quality degradations in a weakly available state.Therefore,accurately modeling cloud systems and mining the hidden system state is crucial.To address this challenge,we propose an anomaly detection method with dynamic spatiotemporal learning(AD-DSTL).AD-DSTL leverages the spatiotemporal dynamics of the system to train an end-to-end deep learning model driven by data from system monitoring to detect underlying anomalous states in complex cloud systems.Unlike previous work that focuses on the KPIs of separate components,AD-DSTL builds a model for the entire system and characterizes its spatiotemporal dynamics based on graph convolutional networks(GCN)and long short-term memory(LSTM).We validated AD-DSTL using four datasets from different backgrounds,and it demonstrated superior robustness compared to other baseline algorithms.Moreover,when raising the target exception level,both the recall and precision of AD-DSTL reached approximately 0.9.Our experimental results demon-strate that AD-DSTL can meet the requirements of anomaly detection for complex cloud systems.展开更多
In order to obtain information or discover knowledge from system logs,the first step is to performlog parsing,whereby unstructured raw logs can be transformed into a sequence of structured events.Although comprehensiv...In order to obtain information or discover knowledge from system logs,the first step is to performlog parsing,whereby unstructured raw logs can be transformed into a sequence of structured events.Although comprehensive studies on log parsing have been conducted in recent years,most assume that one event object corresponds to a single-line message.However,in a growing number of scenarios,one event object spans multiple lines in the log,for which parsing methods toward single-line events are not applicable.In order to address this problem,this paper proposes an automated log parsing method for multiline events(LPME).LPME finds multiline event objects via iterative scanning,driven by a set of heuristic rules derived from practice.The advantage of LPME is that it proposes a cohesion-based evaluation method for multiline events and a bottom-up search approach that eliminates the process of enumerating all combinations.We analyze the algorithmic complexity of LPME and validate it on four datasets from different backgrounds.Evaluations show that the actual time complexity of LPME parsing for multiline events is close to the constant time,which enables it to handle large-scale sample inputs.On the experimental datasets,the performance of LPME achieves 1.0 for recall,and the precision is generally higher than 0.9,which demonstrates the effectiveness of the proposed LPME.展开更多
Modern cloud services are monitored by numerous multidomain and multivendor monitoring tools,which generate massive numbers of alerts and events that are not actionable.These alerts usually carry isolated messages tha...Modern cloud services are monitored by numerous multidomain and multivendor monitoring tools,which generate massive numbers of alerts and events that are not actionable.These alerts usually carry isolated messages that are missing service contexts.Administrators become inundated with tickets caused by such alert events when they are routed directly to incident management systems.Noisy alerts increase the risk of crucial warnings going undetected and leading to service outages.One of the feasible ways to cope with the above problems involves revealing the correlations behind a large number of alerts and then aggregating the related alerts according to their correlations.Based on these guidelines,AlertInsight,a framework for alert event reduction,is proposed in this paper.In AlertInsight,the correlations among event sources are found by mining a sequence of historical events.Then,event correlation knowledge is employed to build an online detector targeting the correlated events that are hidden in the event stream.Finally,the correlated events are aggregated into a single high-level event for alert reduction.Because of theweaknesses of the commonly used pairwise correlation analysis methods in complex environments,an innovative approach for multiple correlation mining,which overcomes computational complexity challenges by scanning panoramic views of historical episodes from the perspective of holism,is proposed in this paper.In addition,a neural network-based correlated event detector that can learn the event correlation knowledge generated from correlation mining and then detect the correlated events in a sequence online is proposed.Experiments are conducted to test the effectiveness of AlertInsight.The experimental results(precision=0.92,recall=0.93,and F1-score=0.93)demonstrate the performance of AlertInsight for the recognition of multiple correlated alerts and its competence for alert reduction.展开更多
Mobile users can be recommended services or goods precisely according to their actual needs even in different contexts. Therefore, it is necessary to construct a framework integrating following functions: context iden...Mobile users can be recommended services or goods precisely according to their actual needs even in different contexts. Therefore, it is necessary to construct a framework integrating following functions: context identification,context reasoning, services or product recommendations and other tasks for the mobile terminal. In this paper, we firstly introduce mobile context awareness theory, and describe the composition of context-aware mobile systems. Secondly, we construct a framework of mobile context-aware recommendation system in line with the characteristics of mobile terminal devices and mobile context-aware data. Then, we build a nested key-value storage model and an up-to-date algorithm for mining mobile context-aware sequential pattern,in order to find both the user’s long-term behavior pattern and the new trend of his recent behavior, to predict user’s next behavior. Lastly, we discuss the difficulties and future development trend of mobile context-aware recommendation system.展开更多
To address identity forgery and privacy leakage in Internet of vehicles(loV)within intelligent transportation systems,we propose an efficient cross-domain identity authentication(IA)scheme based on blockchain and cert...To address identity forgery and privacy leakage in Internet of vehicles(loV)within intelligent transportation systems,we propose an efficient cross-domain identity authentication(IA)scheme based on blockchain and certificateless cryptography.However,existing IA schemes often suffer from high computational overhead,limited scalability,or inadequate support for cross-domain scenarios.First,a distributed authentication architecture is designed,and an offchain storage mechanism combining blockchain and distributed hash table(DHT)to reduce storage costs.Second,a key generation scheme based on certificateless cryptography is designed to address key escrow problem.Third,a conditional privacy protection mechanism is proposed to achieve both anonymity and traceability of vehicle identities.A formal privacy evaluation is provided based on k-anonymity quantifies anonymity level under realistic adversary models.Finally,performance evaluations are conducted in terms of authentication delay,throughput,and success rate,demonstrating that the proposed scheme improves authentication efficiency while enhancing the system security and privacy.展开更多
This paper studies the formation control problem for the second-order heterogeneous nonlinear multi-agent systems(MASs)with switching topology and quantized control inputs.Compared with formation control under the fix...This paper studies the formation control problem for the second-order heterogeneous nonlinear multi-agent systems(MASs)with switching topology and quantized control inputs.Compared with formation control under the fixed topology,under the switching topology inherent nonlinear dynamics of the agent and the connectivity change of the communication topology are considered.Moreover,to avoid the chattering phenomenon caused by unknown input disturbances,the hysteretic quantizers are incorporated to quantize the input signals.By using the Lyapunov stability theory and leader-follower formation approach,the proposed formation control scheme ensures that all signals of the MASs are semi-globally uniformly ultimately bounded(SGUUB).Finally,the efficiency of the theoretical results is proved by a simulation example.展开更多
As a fundamental operation in LBS(location-based services),the trajectory similarity of moving objects has been extensively studied in recent years.However,due to the increasing volume of moving object trajectories an...As a fundamental operation in LBS(location-based services),the trajectory similarity of moving objects has been extensively studied in recent years.However,due to the increasing volume of moving object trajectories and the demand of interactive query performance,the trajectory similarity queries are now required to be processed on massive datasets in a real-time manner.Existing work has proposed distributed or parallel solutions to enable large-scale trajectory similarity processing.However,those techniques cannot be directly adapted to the real-time scenario as it is likely to generate poor balancing performance when workload variance occurs on the incoming trajectory stream.In this paper,we propose a new workload partitioning framework,ART(Adaptive Framework for Real-Time Trajectory Similarity),which introduces practical algorithms to support dynamic workload assignment for RTTS(real-time trajectory similarity).Our proposal includes a processing model tailored for the RTTS scenario,a load balancing framework to maximize throughput,and an adaptive data partition manner designed to cut off unnecessary network cost.Based on this,our model can handle the large-scale trajectory similarity in an on-line scenario,which achieves scalability,effectiveness,and efficiency by a single shot.Empirical studies on synthetic data and real-world stream applications validate the usefulness of our proposal and prove the huge advantage of our approach over state-of-the-art solutions in the literature.展开更多
1 Introduction Empathy is an essential human trait,which reflects the ability of understanding and reflecting on the thoughts and feelings of others.The empathetic dialogue system can improve user's experience and...1 Introduction Empathy is an essential human trait,which reflects the ability of understanding and reflecting on the thoughts and feelings of others.The empathetic dialogue system can improve user's experience and establishlong-termhuman-machine interaction.Perceiving speaker's emotions and predict response's emotions are necessary steps in empathetic dialogue generation.展开更多
基金supported by the National Key Research and Development Program of China (2022YFB4500800).
文摘As cloud system architectures evolve continuously,the interac-tions among distributed components in various roles become increasingly complex.This complexity makes it difficult to detect anomalies in cloud systems.The system status can no longer be determined through individual key performance indicators(KPIs)but through joint judgments based on syn-ergistic relationships among distributed components.Furthermore,anomalies in modern cloud systems are usually not sudden crashes but rather grad-ual,chronic,localized failures or quality degradations in a weakly available state.Therefore,accurately modeling cloud systems and mining the hidden system state is crucial.To address this challenge,we propose an anomaly detection method with dynamic spatiotemporal learning(AD-DSTL).AD-DSTL leverages the spatiotemporal dynamics of the system to train an end-to-end deep learning model driven by data from system monitoring to detect underlying anomalous states in complex cloud systems.Unlike previous work that focuses on the KPIs of separate components,AD-DSTL builds a model for the entire system and characterizes its spatiotemporal dynamics based on graph convolutional networks(GCN)and long short-term memory(LSTM).We validated AD-DSTL using four datasets from different backgrounds,and it demonstrated superior robustness compared to other baseline algorithms.Moreover,when raising the target exception level,both the recall and precision of AD-DSTL reached approximately 0.9.Our experimental results demon-strate that AD-DSTL can meet the requirements of anomaly detection for complex cloud systems.
文摘In order to obtain information or discover knowledge from system logs,the first step is to performlog parsing,whereby unstructured raw logs can be transformed into a sequence of structured events.Although comprehensive studies on log parsing have been conducted in recent years,most assume that one event object corresponds to a single-line message.However,in a growing number of scenarios,one event object spans multiple lines in the log,for which parsing methods toward single-line events are not applicable.In order to address this problem,this paper proposes an automated log parsing method for multiline events(LPME).LPME finds multiline event objects via iterative scanning,driven by a set of heuristic rules derived from practice.The advantage of LPME is that it proposes a cohesion-based evaluation method for multiline events and a bottom-up search approach that eliminates the process of enumerating all combinations.We analyze the algorithmic complexity of LPME and validate it on four datasets from different backgrounds.Evaluations show that the actual time complexity of LPME parsing for multiline events is close to the constant time,which enables it to handle large-scale sample inputs.On the experimental datasets,the performance of LPME achieves 1.0 for recall,and the precision is generally higher than 0.9,which demonstrates the effectiveness of the proposed LPME.
文摘Modern cloud services are monitored by numerous multidomain and multivendor monitoring tools,which generate massive numbers of alerts and events that are not actionable.These alerts usually carry isolated messages that are missing service contexts.Administrators become inundated with tickets caused by such alert events when they are routed directly to incident management systems.Noisy alerts increase the risk of crucial warnings going undetected and leading to service outages.One of the feasible ways to cope with the above problems involves revealing the correlations behind a large number of alerts and then aggregating the related alerts according to their correlations.Based on these guidelines,AlertInsight,a framework for alert event reduction,is proposed in this paper.In AlertInsight,the correlations among event sources are found by mining a sequence of historical events.Then,event correlation knowledge is employed to build an online detector targeting the correlated events that are hidden in the event stream.Finally,the correlated events are aggregated into a single high-level event for alert reduction.Because of theweaknesses of the commonly used pairwise correlation analysis methods in complex environments,an innovative approach for multiple correlation mining,which overcomes computational complexity challenges by scanning panoramic views of historical episodes from the perspective of holism,is proposed in this paper.In addition,a neural network-based correlated event detector that can learn the event correlation knowledge generated from correlation mining and then detect the correlated events in a sequence online is proposed.Experiments are conducted to test the effectiveness of AlertInsight.The experimental results(precision=0.92,recall=0.93,and F1-score=0.93)demonstrate the performance of AlertInsight for the recognition of multiple correlated alerts and its competence for alert reduction.
文摘Mobile users can be recommended services or goods precisely according to their actual needs even in different contexts. Therefore, it is necessary to construct a framework integrating following functions: context identification,context reasoning, services or product recommendations and other tasks for the mobile terminal. In this paper, we firstly introduce mobile context awareness theory, and describe the composition of context-aware mobile systems. Secondly, we construct a framework of mobile context-aware recommendation system in line with the characteristics of mobile terminal devices and mobile context-aware data. Then, we build a nested key-value storage model and an up-to-date algorithm for mining mobile context-aware sequential pattern,in order to find both the user’s long-term behavior pattern and the new trend of his recent behavior, to predict user’s next behavior. Lastly, we discuss the difficulties and future development trend of mobile context-aware recommendation system.
基金supported by the National Natural Science Foundation of China under Grand 62471121.
文摘To address identity forgery and privacy leakage in Internet of vehicles(loV)within intelligent transportation systems,we propose an efficient cross-domain identity authentication(IA)scheme based on blockchain and certificateless cryptography.However,existing IA schemes often suffer from high computational overhead,limited scalability,or inadequate support for cross-domain scenarios.First,a distributed authentication architecture is designed,and an offchain storage mechanism combining blockchain and distributed hash table(DHT)to reduce storage costs.Second,a key generation scheme based on certificateless cryptography is designed to address key escrow problem.Third,a conditional privacy protection mechanism is proposed to achieve both anonymity and traceability of vehicle identities.A formal privacy evaluation is provided based on k-anonymity quantifies anonymity level under realistic adversary models.Finally,performance evaluations are conducted in terms of authentication delay,throughput,and success rate,demonstrating that the proposed scheme improves authentication efficiency while enhancing the system security and privacy.
基金supported by the National Natural Science Foundation of China under Grant Nos.U22A2043 and 61822307。
文摘This paper studies the formation control problem for the second-order heterogeneous nonlinear multi-agent systems(MASs)with switching topology and quantized control inputs.Compared with formation control under the fixed topology,under the switching topology inherent nonlinear dynamics of the agent and the connectivity change of the communication topology are considered.Moreover,to avoid the chattering phenomenon caused by unknown input disturbances,the hysteretic quantizers are incorporated to quantize the input signals.By using the Lyapunov stability theory and leader-follower formation approach,the proposed formation control scheme ensures that all signals of the MASs are semi-globally uniformly ultimately bounded(SGUUB).Finally,the efficiency of the theoretical results is proved by a simulation example.
基金the National Natural Science Foundation of China under Grant Nos.61802273,61772356,and 61836007the Postdoctoral Science Foundation of China under Grant No.2017M621813+2 种基金the Postdoctoral Science Foundation of Jiangsu Province of China under Grant No.2018K029Cthe Natural Science Foundation for Colleges and Universities in Jiangsu Province of China under Grant No.18KJB520044the Open Program of Neusoft Corporation under Grant No.SKLSAOP1801 and Blockshine Technology Corporation of China.
文摘As a fundamental operation in LBS(location-based services),the trajectory similarity of moving objects has been extensively studied in recent years.However,due to the increasing volume of moving object trajectories and the demand of interactive query performance,the trajectory similarity queries are now required to be processed on massive datasets in a real-time manner.Existing work has proposed distributed or parallel solutions to enable large-scale trajectory similarity processing.However,those techniques cannot be directly adapted to the real-time scenario as it is likely to generate poor balancing performance when workload variance occurs on the incoming trajectory stream.In this paper,we propose a new workload partitioning framework,ART(Adaptive Framework for Real-Time Trajectory Similarity),which introduces practical algorithms to support dynamic workload assignment for RTTS(real-time trajectory similarity).Our proposal includes a processing model tailored for the RTTS scenario,a load balancing framework to maximize throughput,and an adaptive data partition manner designed to cut off unnecessary network cost.Based on this,our model can handle the large-scale trajectory similarity in an on-line scenario,which achieves scalability,effectiveness,and efficiency by a single shot.Empirical studies on synthetic data and real-world stream applications validate the usefulness of our proposal and prove the huge advantage of our approach over state-of-the-art solutions in the literature.
基金supported by the National Natural Science Foundation of China (Grant Nos.61672144,61872072).
文摘1 Introduction Empathy is an essential human trait,which reflects the ability of understanding and reflecting on the thoughts and feelings of others.The empathetic dialogue system can improve user's experience and establishlong-termhuman-machine interaction.Perceiving speaker's emotions and predict response's emotions are necessary steps in empathetic dialogue generation.
