The Experts below are selected from a list of 98799 Experts worldwide ranked by ideXlab platform
Yuko Maruyama - One of the best experts on this subject based on the ideXlab platform.
-
Dynamic syslog mining for Network Failure monitoring
Proceeding of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining - KDD '05, 2005Co-Authors: Kenji Yamanishi, Yuko MaruyamaAbstract:Syslog monitoring technologies have recently received vast attentions in the areas of Network management and Network monitoring. They are used to address a wide range of important issues including Network Failure symptom detection and event correlation discovery. Syslogs are intrinsically dynamic in the sense that they form a time series and that their behavior may change over time. This paper proposes a new methodology of dynamic syslog mining in order to detect Failure symptoms with higher confidence and to discover sequential alarm patterns among computer devices. The key ideas of dynamic syslog mining are 1) to represent syslog behavior using a mixture of Hidden Markov Models, 2) to adaptively learn the model using an on-line discounting learning algorithm in combination with dynamic selection of the optimal number of mixture components, and 3) to give anomaly scores using universal test statistics with a dynamically optimized threshold. Using real syslog data we demonstrate the validity of our methodology in the scenarios of Failure symptom detection, emerging pattern identification, and correlation discovery.
-
KDD - Dynamic syslog mining for Network Failure monitoring
Proceeding of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining - KDD '05, 2005Co-Authors: Kenji Yamanishi, Yuko MaruyamaAbstract:Syslog monitoring technologies have recently received vast attentions in the areas of Network management and Network monitoring. They are used to address a wide range of important issues including Network Failure symptom detection and event correlation discovery. Syslogs are intrinsically dynamic in the sense that they form a time series and that their behavior may change over time. This paper proposes a new methodology of dynamic syslog mining in order to detect Failure symptoms with higher confidence and to discover sequential alarm patterns among computer devices. The key ideas of dynamic syslog mining are 1) to represent syslog behavior using a mixture of Hidden Markov Models, 2) to adaptively learn the model using an on-line discounting learning algorithm in combination with dynamic selection of the optimal number of mixture components, and 3) to give anomaly scores using universal test statistics with a dynamically optimized threshold. Using real syslog data we demonstrate the validity of our methodology in the scenarios of Failure symptom detection, emerging pattern identification, and correlation discovery.
Kenji Yamanishi - One of the best experts on this subject based on the ideXlab platform.
-
Dynamic syslog mining for Network Failure monitoring
Proceeding of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining - KDD '05, 2005Co-Authors: Kenji Yamanishi, Yuko MaruyamaAbstract:Syslog monitoring technologies have recently received vast attentions in the areas of Network management and Network monitoring. They are used to address a wide range of important issues including Network Failure symptom detection and event correlation discovery. Syslogs are intrinsically dynamic in the sense that they form a time series and that their behavior may change over time. This paper proposes a new methodology of dynamic syslog mining in order to detect Failure symptoms with higher confidence and to discover sequential alarm patterns among computer devices. The key ideas of dynamic syslog mining are 1) to represent syslog behavior using a mixture of Hidden Markov Models, 2) to adaptively learn the model using an on-line discounting learning algorithm in combination with dynamic selection of the optimal number of mixture components, and 3) to give anomaly scores using universal test statistics with a dynamically optimized threshold. Using real syslog data we demonstrate the validity of our methodology in the scenarios of Failure symptom detection, emerging pattern identification, and correlation discovery.
-
KDD - Dynamic syslog mining for Network Failure monitoring
Proceeding of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining - KDD '05, 2005Co-Authors: Kenji Yamanishi, Yuko MaruyamaAbstract:Syslog monitoring technologies have recently received vast attentions in the areas of Network management and Network monitoring. They are used to address a wide range of important issues including Network Failure symptom detection and event correlation discovery. Syslogs are intrinsically dynamic in the sense that they form a time series and that their behavior may change over time. This paper proposes a new methodology of dynamic syslog mining in order to detect Failure symptoms with higher confidence and to discover sequential alarm patterns among computer devices. The key ideas of dynamic syslog mining are 1) to represent syslog behavior using a mixture of Hidden Markov Models, 2) to adaptively learn the model using an on-line discounting learning algorithm in combination with dynamic selection of the optimal number of mixture components, and 3) to give anomaly scores using universal test statistics with a dynamically optimized threshold. Using real syslog data we demonstrate the validity of our methodology in the scenarios of Failure symptom detection, emerging pattern identification, and correlation discovery.
Behnam Tootooni - One of the best experts on this subject based on the ideXlab platform.
-
a humanitarian logistics model for disaster relief operation considering Network Failure and standard relief time a case study on san francisco district
Transportation Research Part E-logistics and Transportation Review, 2015Co-Authors: Morteza Ahmadi, Abbas Seifi, Behnam TootooniAbstract:We propose a multi-depot location-routing model considering Network Failure, multiple uses of vehicles, and standard relief time. The model determines the locations of local depots and routing for last mile distribution after an earthquake. The model is extended to a two-stage stochastic program with random travel time to ascertain the locations of distribution centers. Small instances have been solved to optimality in GAMS. A variable neighborhood search algorithm is devised to solve the deterministic model. Computational results of our case study show that the unsatisfied demands can be significantly reduced at the cost of higher number of local depots and vehicles.
Masato Oguchi - One of the best experts on this subject based on the ideXlab platform.
-
Network Failure detection system for traffic control using social information in large scale disasters
2015 ITU Kaleidoscope: Trust in the Information Society (K-2015), 2015Co-Authors: Chihiro Maru, Miki Enoki, Akihiro Nakao, Shu Yamamoto, Saneyasu Yamaguchi, Masato OguchiAbstract:When the Great East Japan Earthquake occurred in 2011, it was difficult to grasp all Network conditions immediately using only information from sensors because the damage was considerably heavy and the severe congestion control state occurred. Moreover, at the time of the earthquake, telephone and Internet could not be used in many cases, although Twitter was still available. In an emergency, such as an earthquake, users take an interest in the Network condition and provide information on Networks proactively through social media. Therefore, the collective intelligence of Twitter is suitable as a means of information detection complementary to conventional observation. In this paper, we propose a Network Failure detection system that detects candidates of Failures of telephony infrastructure by utilizing the collective intelligence of social Networking services. By using this system, more information, which is useful for traffic control, can be detected.
-
Kaleidoscope - Network Failure detection system for traffic control using social information in large-scale disasters
2015 ITU Kaleidoscope: Trust in the Information Society (K-2015), 2015Co-Authors: Chihiro Maru, Miki Enoki, Akihiro Nakao, Shu Yamamoto, Saneyasu Yamaguchi, Masato OguchiAbstract:When the Great East Japan Earthquake occurred in 2011, it was difficult to grasp all Network conditions immediately using only information from sensors because the damage was considerably heavy and the severe congestion control state occurred. Moreover, at the time of the earthquake, telephone and Internet could not be used in many cases, although Twitter was still available. In an emergency, such as an earthquake, users take an interest in the Network condition and provide information on Networks proactively through social media. Therefore, the collective intelligence of Twitter is suitable as a means of information detection complementary to conventional observation. In this paper, we propose a Network Failure detection system that detects candidates of Failures of telephony infrastructure by utilizing the collective intelligence of social Networking services. By using this system, more information, which is useful for traffic control, can be detected.
T. Kozlik - One of the best experts on this subject based on the ideXlab platform.
-
IPCCC - An open solution to fault-tolerant Ethernet: design, prototyping, and evaluation
1999 IEEE International Performance Computing and Communications Conference (Cat. No.99CH36305), 1999Co-Authors: J Huang, P. Kappler, R. Freimark, Jeff Gustin, L. Li, S Song, T. KozlikAbstract:Presented is an open solution based approach to fault tolerant Ethernet for process control Networks. This unique approach provides fault tolerance capability that requires no change of vendor hardware (Ethernet physical link and Network Interface Card) and software (Ethernet driver and protocol), yet it is transparent to control applications. The open fault tolerant Ethernet (OFTE) developed based on this approach performs Failure detection and recovery for handling single point of Network Failure and serves regular IP traffic. Our experimentation shows that OFTE performs efficiently, achieving less than 1 ms end to end LAN swapping time and less than 2 sec failover time, and that concurrent application and system loads have little impact on the performance of Failure detection and recovery operations.