Discrimination of seismicity distributed in different areas is essential for reliable seismic risk assessment in mines.Although machine learning has been widely applied in seismic data processing,feasibility and relia...Discrimination of seismicity distributed in different areas is essential for reliable seismic risk assessment in mines.Although machine learning has been widely applied in seismic data processing,feasibility and reliability of applying this technique to classify spatially clustered seismic events in underground mines are yet to be investigated.In this research,two groups of seismic events with a minimum local magnitude(ML) of-3 were observed in an underground coal mine.They were respectively located around a dyke and the longwall face.Additionally,two types of undesired signals were also recorded.Four machine learning methods,i.e.random forest(RF),support vector machine(SVM),deep convolutional neural network(DCNN),and residual neural network(ResNN),were used for classifying these signals.The results obtained based on a primary dataset showed that these seismic events could be classified with at least 91% accuracy.The DCNN using seismogram images as the inputs reached the best performance with more than 94% accuracy.As mining is a dynamic progress which could change the characteristics of seismic signals,the temporal variance in the prediction performance of DCNN was also investigated to assess the reliability of this classifier during mining.A cascaded workflow consisting of database update,model training,signal prediction,and results review was established.By progressively calibrating the DCNN model,it achieved up to 99% prediction accuracy.The results demonstrated that machine learning is a reliable tool for the automatic discrimination of spatially clustered seismicity in underground mining.展开更多
Updating or conditioning a body of evidence modeled within the DS framework plays an important role in most of Artificial Intelligence (AI) applications. Rule is one of the most important methods to represent knowledg...Updating or conditioning a body of evidence modeled within the DS framework plays an important role in most of Artificial Intelligence (AI) applications. Rule is one of the most important methods to represent knowledge in AI. The appearance of uncertain reasoning urges us to measure the belief of rule. Now,most of uncertain reasoning models represent the belief of rule by conditional probability. However,it has many limitations when standard conditional probability is used to measure the belief of expert system rule. In this paper,AI rule is modelled by conditional event and the belief of rule is measured by conditional event probability,then we use random conditional event to construct a new evidence updating method. It can overcome the drawback of the existed methods that the forms of focal sets influence updating result. Some examples are given to illustrate the effectiveness of the proposed method.展开更多
The correctness of workflow models is one of the major challenges in context of workflow analysis. The aim of this paper is to provide an improved Petri net-based reduction approach for verifying the correctness of wo...The correctness of workflow models is one of the major challenges in context of workflow analysis. The aim of this paper is to provide an improved Petri net-based reduction approach for verifying the correctness of workflow models. To the end, how to represent well-behaved building blocks and control structures of business processes by Petri nets is given at first, and then how to build well-structured process nets is presented. According to the structural characteristics of well-structured process nets, a set of legacy reduction rules are improved and extended, and then a complete Petri-net-based verification approach is proposed. The sound ness and the complexity with polynomial time for the improved re duction method are also proven.展开更多
Many workflow management systems have emerged in recent years, but few of them provide any form of support for verification. This frequently results in runtime errors that need to be corrected at prohibitive costs. In...Many workflow management systems have emerged in recent years, but few of them provide any form of support for verification. This frequently results in runtime errors that need to be corrected at prohibitive costs. In Ref.[1], a few reduction rules of verifying workflow graph are given. After analyzing the reduction rules, the overlapped reduction rule is found to be inaccurate. In this paper, the improved reduction rules are presented and the matrix-based implementing algorithm is given, so that the scope of the verification of workflow is expanded and the efficiency of the algorithm is enhanced. The method is simple and natural, and its implementation is easy too.展开更多
With the advances of electronic information technology and computer network, especially the embedded technology, smart home is no more just a vision but being practical. The interoperability of heterogeneous devices a...With the advances of electronic information technology and computer network, especially the embedded technology, smart home is no more just a vision but being practical. The interoperability of heterogeneous devices and flexibility of devices' usage are two key problems that challenge the implementation of smart home. To deal with these two issues, this paper proposes an event-driven service oriented architecture using device profile for web services (DPWS). DPWS inherits the advantages of the traditional web services in achieving interoperability without dependence on platform, while improving service discovery and security as well as being optimized for deploying on resource constrained devices. By providing a visual interface for describing a service workflow (SW), the user can easily customize the actions of devices by services composition. Devices automatically cooperate without user's intervention to complete required business logic. This is achieved by fully exploiting the eventing capabilities on DPWS enabled home devices. Finally, a home theater scenario is given to illustrate the event driven mechanism for the SW in the proposed smart home framework.展开更多
FDES(fuzzy discrete event systems) can effectively represent a kind of complicated systems involving deterministic uncertainties and vagueness as well as human subjective observation and judgement from the view of dis...FDES(fuzzy discrete event systems) can effectively represent a kind of complicated systems involving deterministic uncertainties and vagueness as well as human subjective observation and judgement from the view of discrete events, here the information system is divided into some independent intelligent entitative Agents. The concept of information processing state based on Agents was proposed. The processing state of Agent can be judged by some assistant observation parameters about the Agent and its environment around, and the transition among these states can be represented by FDES based on rules. In order to ensure the harmony of the Agents for information processing, its upstream and downstream buffers are considered in the modeling of the Agent system, and the supervisory controller based on FDES is constructed. The processing state of Agent can be adjusted by the supervisory controller to improve the stability of the system and the efficiency of resource utilization during the process according to the control policies. The result of its application was provided to illustrate the validity of the supervisory adjustment.展开更多
Focusing on the problem of goal event detection in soccer videos,a novel method based on Hidden Markov Model(HMM) and the semantic rule is proposed.Firstly,a HMM for a goal event is constructed.Then a Normalized Seman...Focusing on the problem of goal event detection in soccer videos,a novel method based on Hidden Markov Model(HMM) and the semantic rule is proposed.Firstly,a HMM for a goal event is constructed.Then a Normalized Semantic Weighted Sum(NSWS) rule is established by defining a new feature of shots,semantic observation weight.The test video is detected based on the HMM and the NSWS rule,respectively.Finally,a fusion scheme based on logic distance is proposed and the detection results of the HMM and the NSWS rule are fused by optimal weights in the decision level,obtaining the final result.Experimental results indicate that the proposed method achieves 96.43% precision and 100% recall,which shows the effectiveness of this letter.展开更多
With the vehement development of global competition , Agile Supply Chain (ASC) becomes an effective approach that supports dynamic ent erprise alliance and realizes agile manufacturing, as for the enterprises to cap t...With the vehement development of global competition , Agile Supply Chain (ASC) becomes an effective approach that supports dynamic ent erprise alliance and realizes agile manufacturing, as for the enterprises to cap ture market opportunities rapidly and strengthen their anti-risk ability. As Ag ile Supply Chain System (ASCS) is dynamic and distributed, the realization of it ’s processes needs to be much flexible. Often in Agile Supply Chain System (ASCS ), there are many dynamic tasks, many changes of the processes, and cooperative workflows, which need the workflows able to be adjusted agilely and smoothly, no t much affecting others. This paper will propose a flexible workflow management for achieving the agility and compatibility. At the first of the paper, we will discuss the situation in which Agile Supply C hain System is applied, and then we will elaborate the characteristics of Agile Supply Chain System. So with that, the shortcomings of the process managements t hat are, at present, used in Supply Chain Systems will be displayed clearly. The n, the proposal will be given in the paper, to resolve the problems in the prese nt process management in ASCS. We will see supply chain systems implemented mult i-agent-based technology to adapt to the dynamic environment, however in many systems, coordination of the workflows is executed by the explicit messages comm unicated between the agents. This will lead to a tightly coupled system. To over come it, the paper suggests the workflow management in agent-based ASCS using t he Events-Triggering mechanism, instead of the explicit messages. We create Eve nts-Triggering contents and rules, having push-pull mechanism, event-state se t and triggering-conditions, and store them in the distributed database subject ed to the corresponding agents. Adjusting the Events-Triggering data will be us ed to adapt to the dynamic tasks and the changes of processes. In sum, we will p resent the methods of process modeling, the system structure, and the executing -mechanism of the flexible workflow management we propose in the paper. Also, t he paper outlines several exception-handling policies for the flexible workflow management, in succession. And at the final of the paper, we discuss the realiz ation of the flexible workflow management in Agile Supply Chain System. The flex ible workflow management will be implemented using CORBA services and Java techn ology for the distributed systems. CORBA is chosen as the specification of distr ibuted electronic data exchange, and Java as the construction tool of the system . The framework of the flexible workflow management constructed on them is showe d in the paper.展开更多
基金the Australia Coal Association Research Program(ACARP)(Grant Nos.C26006 and C26053)Supports from CSIRO。
文摘Discrimination of seismicity distributed in different areas is essential for reliable seismic risk assessment in mines.Although machine learning has been widely applied in seismic data processing,feasibility and reliability of applying this technique to classify spatially clustered seismic events in underground mines are yet to be investigated.In this research,two groups of seismic events with a minimum local magnitude(ML) of-3 were observed in an underground coal mine.They were respectively located around a dyke and the longwall face.Additionally,two types of undesired signals were also recorded.Four machine learning methods,i.e.random forest(RF),support vector machine(SVM),deep convolutional neural network(DCNN),and residual neural network(ResNN),were used for classifying these signals.The results obtained based on a primary dataset showed that these seismic events could be classified with at least 91% accuracy.The DCNN using seismogram images as the inputs reached the best performance with more than 94% accuracy.As mining is a dynamic progress which could change the characteristics of seismic signals,the temporal variance in the prediction performance of DCNN was also investigated to assess the reliability of this classifier during mining.A cascaded workflow consisting of database update,model training,signal prediction,and results review was established.By progressively calibrating the DCNN model,it achieved up to 99% prediction accuracy.The results demonstrated that machine learning is a reliable tool for the automatic discrimination of spatially clustered seismicity in underground mining.
基金Supported by the NSFC (No. 60772006, 60874105)the ZJNSF (Y1080422, R106745)Aviation Science Foundation (20070511001)
文摘Updating or conditioning a body of evidence modeled within the DS framework plays an important role in most of Artificial Intelligence (AI) applications. Rule is one of the most important methods to represent knowledge in AI. The appearance of uncertain reasoning urges us to measure the belief of rule. Now,most of uncertain reasoning models represent the belief of rule by conditional probability. However,it has many limitations when standard conditional probability is used to measure the belief of expert system rule. In this paper,AI rule is modelled by conditional event and the belief of rule is measured by conditional event probability,then we use random conditional event to construct a new evidence updating method. It can overcome the drawback of the existed methods that the forms of focal sets influence updating result. Some examples are given to illustrate the effectiveness of the proposed method.
基金Supported by the Scientific Research Foundation of Edu-cation Agency of Liaoning Province (20040088) and Scientific ResearchFoundation of Dalian Nationalities University (20046202)
文摘The correctness of workflow models is one of the major challenges in context of workflow analysis. The aim of this paper is to provide an improved Petri net-based reduction approach for verifying the correctness of workflow models. To the end, how to represent well-behaved building blocks and control structures of business processes by Petri nets is given at first, and then how to build well-structured process nets is presented. According to the structural characteristics of well-structured process nets, a set of legacy reduction rules are improved and extended, and then a complete Petri-net-based verification approach is proposed. The sound ness and the complexity with polynomial time for the improved re duction method are also proven.
文摘Many workflow management systems have emerged in recent years, but few of them provide any form of support for verification. This frequently results in runtime errors that need to be corrected at prohibitive costs. In Ref.[1], a few reduction rules of verifying workflow graph are given. After analyzing the reduction rules, the overlapped reduction rule is found to be inaccurate. In this paper, the improved reduction rules are presented and the matrix-based implementing algorithm is given, so that the scope of the verification of workflow is expanded and the efficiency of the algorithm is enhanced. The method is simple and natural, and its implementation is easy too.
文摘With the advances of electronic information technology and computer network, especially the embedded technology, smart home is no more just a vision but being practical. The interoperability of heterogeneous devices and flexibility of devices' usage are two key problems that challenge the implementation of smart home. To deal with these two issues, this paper proposes an event-driven service oriented architecture using device profile for web services (DPWS). DPWS inherits the advantages of the traditional web services in achieving interoperability without dependence on platform, while improving service discovery and security as well as being optimized for deploying on resource constrained devices. By providing a visual interface for describing a service workflow (SW), the user can easily customize the actions of devices by services composition. Devices automatically cooperate without user's intervention to complete required business logic. This is achieved by fully exploiting the eventing capabilities on DPWS enabled home devices. Finally, a home theater scenario is given to illustrate the event driven mechanism for the SW in the proposed smart home framework.
文摘FDES(fuzzy discrete event systems) can effectively represent a kind of complicated systems involving deterministic uncertainties and vagueness as well as human subjective observation and judgement from the view of discrete events, here the information system is divided into some independent intelligent entitative Agents. The concept of information processing state based on Agents was proposed. The processing state of Agent can be judged by some assistant observation parameters about the Agent and its environment around, and the transition among these states can be represented by FDES based on rules. In order to ensure the harmony of the Agents for information processing, its upstream and downstream buffers are considered in the modeling of the Agent system, and the supervisory controller based on FDES is constructed. The processing state of Agent can be adjusted by the supervisory controller to improve the stability of the system and the efficiency of resource utilization during the process according to the control policies. The result of its application was provided to illustrate the validity of the supervisory adjustment.
基金Supported by the National Natural Science Foundation of China (No. 61072110)the Industrial Tackling Project of Shaanxi Province (2010K06-20)the Natural Science Foundation of Shaanxi Province (SJ08F15)
文摘Focusing on the problem of goal event detection in soccer videos,a novel method based on Hidden Markov Model(HMM) and the semantic rule is proposed.Firstly,a HMM for a goal event is constructed.Then a Normalized Semantic Weighted Sum(NSWS) rule is established by defining a new feature of shots,semantic observation weight.The test video is detected based on the HMM and the NSWS rule,respectively.Finally,a fusion scheme based on logic distance is proposed and the detection results of the HMM and the NSWS rule are fused by optimal weights in the decision level,obtaining the final result.Experimental results indicate that the proposed method achieves 96.43% precision and 100% recall,which shows the effectiveness of this letter.
文摘With the vehement development of global competition , Agile Supply Chain (ASC) becomes an effective approach that supports dynamic ent erprise alliance and realizes agile manufacturing, as for the enterprises to cap ture market opportunities rapidly and strengthen their anti-risk ability. As Ag ile Supply Chain System (ASCS) is dynamic and distributed, the realization of it ’s processes needs to be much flexible. Often in Agile Supply Chain System (ASCS ), there are many dynamic tasks, many changes of the processes, and cooperative workflows, which need the workflows able to be adjusted agilely and smoothly, no t much affecting others. This paper will propose a flexible workflow management for achieving the agility and compatibility. At the first of the paper, we will discuss the situation in which Agile Supply C hain System is applied, and then we will elaborate the characteristics of Agile Supply Chain System. So with that, the shortcomings of the process managements t hat are, at present, used in Supply Chain Systems will be displayed clearly. The n, the proposal will be given in the paper, to resolve the problems in the prese nt process management in ASCS. We will see supply chain systems implemented mult i-agent-based technology to adapt to the dynamic environment, however in many systems, coordination of the workflows is executed by the explicit messages comm unicated between the agents. This will lead to a tightly coupled system. To over come it, the paper suggests the workflow management in agent-based ASCS using t he Events-Triggering mechanism, instead of the explicit messages. We create Eve nts-Triggering contents and rules, having push-pull mechanism, event-state se t and triggering-conditions, and store them in the distributed database subject ed to the corresponding agents. Adjusting the Events-Triggering data will be us ed to adapt to the dynamic tasks and the changes of processes. In sum, we will p resent the methods of process modeling, the system structure, and the executing -mechanism of the flexible workflow management we propose in the paper. Also, t he paper outlines several exception-handling policies for the flexible workflow management, in succession. And at the final of the paper, we discuss the realiz ation of the flexible workflow management in Agile Supply Chain System. The flex ible workflow management will be implemented using CORBA services and Java techn ology for the distributed systems. CORBA is chosen as the specification of distr ibuted electronic data exchange, and Java as the construction tool of the system . The framework of the flexible workflow management constructed on them is showe d in the paper.