�ݺ�ߣshows by User: KooroshAslansefat

�ݺ�ߣshows by User: KooroshAslansefat / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: KooroshAslansefat / Wed, 16 Sep 2020 10:12:53 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: KooroshAslansefat SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical Difference Measure /slideshow/safeml-safety-monitoring-of-machine-learning-classifiers-through-statistical-difference-measure/238508622 safemlimbsav2-200916101253
Ensuring safety and explainability of machine learning (ML) is a topic of increasing relevance as data-driven applications venture into safety-critical application domains, traditionally committed to high safety standards that are not satisfied with an exclusive testing approach of otherwise inaccessible black-box systems. Especially the interaction between safety and security is a central challenge, as security violations can lead to compromised safety. The contribution of this paper to addressing both safety and security within a single concept of protection applicable during the operation of ML systems is active monitoring of the behaviour and the operational context of the data-driven system based on distance measures of the Empirical Cumulative Distribution Function (ECDF). We investigate abstract datasets (XOR, Spiral, Circle) and current security-specific datasets for intrusion detection (CICIDS2017) of simulated network traffic, using distributional shift detection measures including the Kolmogorov-Smirnov, Kuiper, Anderson-Darling, Wasserstein and mixed Wasserstein-Anderson-Darling measures. Our preliminary findings indicate that the approach can provide a basis for detecting whether the application context of an ML component is valid in the safety-security. Our preliminary code and results are available at https://github.com/ISorokos/SafeML. https://arxiv.org/abs/2005.13166]]>
Ensuring safety and explainability of machine learning (ML) is a topic of increasing relevance as data-driven applications venture into safety-critical application domains, traditionally committed to high safety standards that are not satisfied with an exclusive testing approach of otherwise inaccessible black-box systems. Especially the interaction between safety and security is a central challenge, as security violations can lead to compromised safety. The contribution of this paper to addressing both safety and security within a single concept of protection applicable during the operation of ML systems is active monitoring of the behaviour and the operational context of the data-driven system based on distance measures of the Empirical Cumulative Distribution Function (ECDF). We investigate abstract datasets (XOR, Spiral, Circle) and current security-specific datasets for intrusion detection (CICIDS2017) of simulated network traffic, using distributional shift detection measures including the Kolmogorov-Smirnov, Kuiper, Anderson-Darling, Wasserstein and mixed Wasserstein-Anderson-Darling measures. Our preliminary findings indicate that the approach can provide a basis for detecting whether the application context of an ML component is valid in the safety-security. Our preliminary code and results are available at https://github.com/ISorokos/SafeML. https://arxiv.org/abs/2005.13166]]> Wed, 16 Sep 2020 10:12:53 GMT /slideshow/safeml-safety-monitoring-of-machine-learning-classifiers-through-statistical-difference-measure/238508622 KooroshAslansefat@slideshare.net(KooroshAslansefat) SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical Difference Measure KooroshAslansefat Ensuring safety and explainability of machine learning (ML) is a topic of increasing relevance as data-driven applications venture into safety-critical application domains, traditionally committed to high safety standards that are not satisfied with an exclusive testing approach of otherwise inaccessible black-box systems. Especially the interaction between safety and security is a central challenge, as security violations can lead to compromised safety. The contribution of this paper to addressing both safety and security within a single concept of protection applicable during the operation of ML systems is active monitoring of the behaviour and the operational context of the data-driven system based on distance measures of the Empirical Cumulative Distribution Function (ECDF). We investigate abstract datasets (XOR, Spiral, Circle) and current security-specific datasets for intrusion detection (CICIDS2017) of simulated network traffic, using distributional shift detection measures including the Kolmogorov-Smirnov, Kuiper, Anderson-Darling, Wasserstein and mixed Wasserstein-Anderson-Darling measures. Our preliminary findings indicate that the approach can provide a basis for detecting whether the application context of an ML component is valid in the safety-security. Our preliminary code and results are available at https://github.com/ISorokos/SafeML. https://arxiv.org/abs/2005.13166 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/safemlimbsav2-200916101253-thumbnail.jpg?width=120&height=120&fit=bounds" /> Ensuring safety and explainability of machine learning (ML) is a topic of increasing relevance as data-driven applications venture into safety-critical application domains, traditionally committed to high safety standards that are not satisfied with an exclusive testing approach of otherwise inaccessible black-box systems. Especially the interaction between safety and security is a central challenge, as security violations can lead to compromised safety. The contribution of this paper to addressing both safety and security within a single concept of protection applicable during the operation of ML systems is active monitoring of the behaviour and the operational context of the data-driven system based on distance measures of the Empirical Cumulative Distribution Function (ECDF). We investigate abstract datasets (XOR, Spiral, Circle) and current security-specific datasets for intrusion detection (CICIDS2017) of simulated network traffic, using distributional shift detection measures including the Kolmogorov-Smirnov, Kuiper, Anderson-Darling, Wasserstein and mixed Wasserstein-Anderson-Darling measures. Our preliminary findings indicate that the approach can provide a basis for detecting whether the application context of an ML component is valid in the safety-security. Our preliminary code and results are available at https://github.com/ISorokos/SafeML. https://arxiv.org/abs/2005.13166

SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical Difference Measure from Koorosh Aslansefat

]]> 50 0 https://cdn.slidesharecdn.com/ss_thumbnails/safemlimbsav2-200916101253-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Reliability Evaluation of Reconfigurable NMR Architecture Supported with Hot Standby Spare: Markov Modeling and Formulation /slideshow/reliability-evaluation-of-reconfigurable-nmr-architecture-supported-with-hot-standby-spare-markov-modeling-and-formulation/238508532 reliabilityevaluationofreconfigurablenmrarchitecturesupportedwithhotstandbysparemarkovmodelingandfor-200916100924
Reliability is a major issue for fault-tolerant systems used in critical applications. N-modular redundancy (NMR) is one of the traditional approaches used for fault masking in fault-tolerant systems. Reconfigurable NMR architecture supported with hot or cold standby spares is a common industrial method. So far, no systematic method for creating the Markov model of reconfigurable NMR systems supported with hot standby spares has been presented. Likewise, there is no explicit parametric formula for the reliability of these systems in the literature. This paper focuses on two issues: the systematic construction of the Markov model of reconfigurable NMR system, and its evaluation through a precise and explicit formula introduces in this paper. The introduced formula gives for system designer a good view of reliability behaviour of the reconfigurable NMR systems. https://doi.org/10.1007/978-3-030-58920-2_4]]>
Reliability is a major issue for fault-tolerant systems used in critical applications. N-modular redundancy (NMR) is one of the traditional approaches used for fault masking in fault-tolerant systems. Reconfigurable NMR architecture supported with hot or cold standby spares is a common industrial method. So far, no systematic method for creating the Markov model of reconfigurable NMR systems supported with hot standby spares has been presented. Likewise, there is no explicit parametric formula for the reliability of these systems in the literature. This paper focuses on two issues: the systematic construction of the Markov model of reconfigurable NMR system, and its evaluation through a precise and explicit formula introduces in this paper. The introduced formula gives for system designer a good view of reliability behaviour of the reconfigurable NMR systems. https://doi.org/10.1007/978-3-030-58920-2_4]]> Wed, 16 Sep 2020 10:09:24 GMT /slideshow/reliability-evaluation-of-reconfigurable-nmr-architecture-supported-with-hot-standby-spare-markov-modeling-and-formulation/238508532 KooroshAslansefat@slideshare.net(KooroshAslansefat) Reliability Evaluation of Reconfigurable NMR Architecture Supported with Hot Standby Spare: Markov Modeling and Formulation KooroshAslansefat Reliability is a major issue for fault-tolerant systems used in critical applications. N-modular redundancy (NMR) is one of the traditional approaches used for fault masking in fault-tolerant systems. Reconfigurable NMR architecture supported with hot or cold standby spares is a common industrial method. So far, no systematic method for creating the Markov model of reconfigurable NMR systems supported with hot standby spares has been presented. Likewise, there is no explicit parametric formula for the reliability of these systems in the literature. This paper focuses on two issues: the systematic construction of the Markov model of reconfigurable NMR system, and its evaluation through a precise and explicit formula introduces in this paper. The introduced formula gives for system designer a good view of reliability behaviour of the reconfigurable NMR systems. https://doi.org/10.1007/978-3-030-58920-2_4 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/reliabilityevaluationofreconfigurablenmrarchitecturesupportedwithhotstandbysparemarkovmodelingandfor-200916100924-thumbnail.jpg?width=120&height=120&fit=bounds" /> Reliability is a major issue for fault-tolerant systems used in critical applications. N-modular redundancy (NMR) is one of the traditional approaches used for fault masking in fault-tolerant systems. Reconfigurable NMR architecture supported with hot or cold standby spares is a common industrial method. So far, no systematic method for creating the Markov model of reconfigurable NMR systems supported with hot standby spares has been presented. Likewise, there is no explicit parametric formula for the reliability of these systems in the literature. This paper focuses on two issues: the systematic construction of the Markov model of reconfigurable NMR system, and its evaluation through a precise and explicit formula introduces in this paper. The introduced formula gives for system designer a good view of reliability behaviour of the reconfigurable NMR systems. https://doi.org/10.1007/978-3-030-58920-2_4

Reliability Evaluation of Reconfigurable NMR Architecture Supported with Hot Standby Spare: Markov Modeling and Formulation from Koorosh Aslansefat

]]> 21 0 https://cdn.slidesharecdn.com/ss_thumbnails/reliabilityevaluationofreconfigurablenmrarchitecturesupportedwithhotstandbysparemarkovmodelingandfor-200916100924-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 A Conceptual Framework to Incorporate Complex Basic Events in HiP-HOPS /slideshow/a-conceptual-framework-to-incorporate-complex-basic-events-in-hiphops/196011710 aconceptualframeworktoincorporatecomplex-191121122402
Reliability evaluation for ensuring the uninterrupted system operation is an integral part of dependable system development. Model-based safety analysis (MBSA) techniques such as Hierarchically Performed Hazard Origin and Propagation Studies (HiP-HOPS) have made the reliability analysis process less expensive in terms of effort and time required. HiP-HOPS uses an analytical modelling approach for Fault tree analysis to automate the reliability analysis process, where each system component is associated with its failure rate or failure probability. However, such non-state-space analysis models are not capable of modelling more complex failure behaviour of component like failure/repair dependencies, e.g., spares, shared repair, imperfect coverage, etc. State-space based paradigms like Markov chain can model complex failure behaviour, but their use can lead to state-space explosion, thus undermining the overall analysis capacity. Therefore, to maintain the benefits of MBSA while not compromising on modelling capability, in this paper, we propose a conceptual framework to incorporate complex basic events in HiP-HOPS. The idea is demonstrated via an illustrative example. For more information check the following papers: https://doi.org/10.1007/978-3-030-32872-6_8 https://doi.org/10.1109/TR.2019.2923893 https://doi.org/10.1109/ACCESS.2019.2941566]]>
Reliability evaluation for ensuring the uninterrupted system operation is an integral part of dependable system development. Model-based safety analysis (MBSA) techniques such as Hierarchically Performed Hazard Origin and Propagation Studies (HiP-HOPS) have made the reliability analysis process less expensive in terms of effort and time required. HiP-HOPS uses an analytical modelling approach for Fault tree analysis to automate the reliability analysis process, where each system component is associated with its failure rate or failure probability. However, such non-state-space analysis models are not capable of modelling more complex failure behaviour of component like failure/repair dependencies, e.g., spares, shared repair, imperfect coverage, etc. State-space based paradigms like Markov chain can model complex failure behaviour, but their use can lead to state-space explosion, thus undermining the overall analysis capacity. Therefore, to maintain the benefits of MBSA while not compromising on modelling capability, in this paper, we propose a conceptual framework to incorporate complex basic events in HiP-HOPS. The idea is demonstrated via an illustrative example. For more information check the following papers: https://doi.org/10.1007/978-3-030-32872-6_8 https://doi.org/10.1109/TR.2019.2923893 https://doi.org/10.1109/ACCESS.2019.2941566]]> Thu, 21 Nov 2019 12:24:02 GMT /slideshow/a-conceptual-framework-to-incorporate-complex-basic-events-in-hiphops/196011710 KooroshAslansefat@slideshare.net(KooroshAslansefat) A Conceptual Framework to Incorporate Complex Basic Events in HiP-HOPS KooroshAslansefat Reliability evaluation for ensuring the uninterrupted system operation is an integral part of dependable system development. Model-based safety analysis (MBSA) techniques such as Hierarchically Performed Hazard Origin and Propagation Studies (HiP-HOPS) have made the reliability analysis process less expensive in terms of effort and time required. HiP-HOPS uses an analytical modelling approach for Fault tree analysis to automate the reliability analysis process, where each system component is associated with its failure rate or failure probability. However, such non-state-space analysis models are not capable of modelling more complex failure behaviour of component like failure/repair dependencies, e.g., spares, shared repair, imperfect coverage, etc. State-space based paradigms like Markov chain can model complex failure behaviour, but their use can lead to state-space explosion, thus undermining the overall analysis capacity. Therefore, to maintain the benefits of MBSA while not compromising on modelling capability, in this paper, we propose a conceptual framework to incorporate complex basic events in HiP-HOPS. The idea is demonstrated via an illustrative example. For more information check the following papers: https://doi.org/10.1007/978-3-030-32872-6_8 https://doi.org/10.1109/TR.2019.2923893 https://doi.org/10.1109/ACCESS.2019.2941566 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/aconceptualframeworktoincorporatecomplex-191121122402-thumbnail.jpg?width=120&height=120&fit=bounds" /> Reliability evaluation for ensuring the uninterrupted system operation is an integral part of dependable system development. Model-based safety analysis (MBSA) techniques such as Hierarchically Performed Hazard Origin and Propagation Studies (HiP-HOPS) have made the reliability analysis process less expensive in terms of effort and time required. HiP-HOPS uses an analytical modelling approach for Fault tree analysis to automate the reliability analysis process, where each system component is associated with its failure rate or failure probability. However, such non-state-space analysis models are not capable of modelling more complex failure behaviour of component like failure/repair dependencies, e.g., spares, shared repair, imperfect coverage, etc. State-space based paradigms like Markov chain can model complex failure behaviour, but their use can lead to state-space explosion, thus undermining the overall analysis capacity. Therefore, to maintain the benefits of MBSA while not compromising on modelling capability, in this paper, we propose a conceptual framework to incorporate complex basic events in HiP-HOPS. The idea is demonstrated via an illustrative example. For more information check the following papers: https://doi.org/10.1007/978-3-030-32872-6_8 https://doi.org/10.1109/TR.2019.2923893 https://doi.org/10.1109/ACCESS.2019.2941566

A Conceptual Framework to Incorporate Complex Basic Events in HiP-HOPS from Koorosh Aslansefat

]]> 56 0 https://cdn.slidesharecdn.com/ss_thumbnails/aconceptualframeworktoincorporatecomplex-191121122402-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 A markov process based approach for reliability evaluation of the propulsion system in multi-rotor drones presentation /slideshow/a-markov-process-based-approach-for-reliability-evaluation-of-the-propulsion-system-in-multirotor-drones-presentation/146219791 amarkovprocess-basedapproachforreliabilityevaluationofthepropulsionsysteminmulti-rotordronespresenta-190517070508
Autonomous multirotors as a popular type of Unmanned Aerial Vehicles (UAVs) have a tremendous potential to facilitate activities such as logistics, emergency response, recording video, capturing special events, and traffic management. Despite the potential benefits the possibility of harming people during operation should be considered. This paper focuses on modeling multirotors' propulsion system with Markov chains. The validity of the models is proven with a combination of controllability theory and Monte Carlo simulations. Using the proposed model, both reliability and Mean Time To Failure (MTTF) of the propulsion system are evaluated. This study proposes a fault detection and recovery system based on a Markov Model for mission control of multirotors. Concretely, the proposed system aims to reduce potential injuries by increasing safety]]>
Autonomous multirotors as a popular type of Unmanned Aerial Vehicles (UAVs) have a tremendous potential to facilitate activities such as logistics, emergency response, recording video, capturing special events, and traffic management. Despite the potential benefits the possibility of harming people during operation should be considered. This paper focuses on modeling multirotors' propulsion system with Markov chains. The validity of the models is proven with a combination of controllability theory and Monte Carlo simulations. Using the proposed model, both reliability and Mean Time To Failure (MTTF) of the propulsion system are evaluated. This study proposes a fault detection and recovery system based on a Markov Model for mission control of multirotors. Concretely, the proposed system aims to reduce potential injuries by increasing safety]]> Fri, 17 May 2019 07:05:08 GMT /slideshow/a-markov-process-based-approach-for-reliability-evaluation-of-the-propulsion-system-in-multirotor-drones-presentation/146219791 KooroshAslansefat@slideshare.net(KooroshAslansefat) A markov process based approach for reliability evaluation of the propulsion system in multi-rotor drones presentation KooroshAslansefat Autonomous multirotors as a popular type of Unmanned Aerial Vehicles (UAVs) have a tremendous potential to facilitate activities such as logistics, emergency response, recording video, capturing special events, and traffic management. Despite the potential benefits the possibility of harming people during operation should be considered. This paper focuses on modeling multirotors' propulsion system with Markov chains. The validity of the models is proven with a combination of controllability theory and Monte Carlo simulations. Using the proposed model, both reliability and Mean Time To Failure (MTTF) of the propulsion system are evaluated. This study proposes a fault detection and recovery system based on a Markov Model for mission control of multirotors. Concretely, the proposed system aims to reduce potential injuries by increasing safety <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/amarkovprocess-basedapproachforreliabilityevaluationofthepropulsionsysteminmulti-rotordronespresenta-190517070508-thumbnail.jpg?width=120&height=120&fit=bounds" /> Autonomous multirotors as a popular type of Unmanned Aerial Vehicles (UAVs) have a tremendous potential to facilitate activities such as logistics, emergency response, recording video, capturing special events, and traffic management. Despite the potential benefits the possibility of harming people during operation should be considered. This paper focuses on modeling multirotors' propulsion system with Markov chains. The validity of the models is proven with a combination of controllability theory and Monte Carlo simulations. Using the proposed model, both reliability and Mean Time To Failure (MTTF) of the propulsion system are evaluated. This study proposes a fault detection and recovery system based on a Markov Model for mission control of multirotors. Concretely, the proposed system aims to reduce potential injuries by increasing safety

A markov process based approach for reliability evaluation of the propulsion system in multi-rotor drones presentation from Koorosh Aslansefat

]]> 131 1 https://cdn.slidesharecdn.com/ss_thumbnails/amarkovprocess-basedapproachforreliabilityevaluationofthepropulsionsysteminmulti-rotordronespresenta-190517070508-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Resilience Supported System for Innovative Water Monitoring Technology /slideshow/resilience-supported-system-for-innovative-water-monitoring-technology/95828536 03resiliencesupportedsystem-180503140313
The level of intelligence in monitoring & controlling systems are increasing dramatically. The critical issue for an autonomous resilient system is detecting the anomalous behavior through standard patterns to react properly and on time. In cyber-physical systems with the interaction of humans and machines, this will be more complicated. Deceptive alarm is a common dilemma in real systems which could reduce awareness and readiness and accordingly resilience of the system. In this paper, Markov modeling technique is used to predict human behaviors patterns to distinguish between human anomalous behavior and system failure. The data is from the real experience of implementing innovative monitoring system in a five-star hotel which was part of the project of gamification for changing guests’ behavior. The idea was to develop Resilience Supported System to decrease the fault error and alarms and to increase the reliability and resilience of the system. ]]>
The level of intelligence in monitoring & controlling systems are increasing dramatically. The critical issue for an autonomous resilient system is detecting the anomalous behavior through standard patterns to react properly and on time. In cyber-physical systems with the interaction of humans and machines, this will be more complicated. Deceptive alarm is a common dilemma in real systems which could reduce awareness and readiness and accordingly resilience of the system. In this paper, Markov modeling technique is used to predict human behaviors patterns to distinguish between human anomalous behavior and system failure. The data is from the real experience of implementing innovative monitoring system in a five-star hotel which was part of the project of gamification for changing guests’ behavior. The idea was to develop Resilience Supported System to decrease the fault error and alarms and to increase the reliability and resilience of the system. ]]> Thu, 03 May 2018 14:03:13 GMT /slideshow/resilience-supported-system-for-innovative-water-monitoring-technology/95828536 KooroshAslansefat@slideshare.net(KooroshAslansefat) Resilience Supported System for Innovative Water Monitoring Technology KooroshAslansefat The level of intelligence in monitoring & controlling systems are increasing dramatically. The critical issue for an autonomous resilient system is detecting the anomalous behavior through standard patterns to react properly and on time. In cyber-physical systems with the interaction of humans and machines, this will be more complicated. Deceptive alarm is a common dilemma in real systems which could reduce awareness and readiness and accordingly resilience of the system. In this paper, Markov modeling technique is used to predict human behaviors patterns to distinguish between human anomalous behavior and system failure. The data is from the real experience of implementing innovative monitoring system in a five-star hotel which was part of the project of gamification for changing guests’ behavior. The idea was to develop Resilience Supported System to decrease the fault error and alarms and to increase the reliability and resilience of the system. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/03resiliencesupportedsystem-180503140313-thumbnail.jpg?width=120&height=120&fit=bounds" /> The level of intelligence in monitoring & controlling systems are increasing dramatically. The critical issue for an autonomous resilient system is detecting the anomalous behavior through standard patterns to react properly and on time. In cyber-physical systems with the interaction of humans and machines, this will be more complicated. Deceptive alarm is a common dilemma in real systems which could reduce awareness and readiness and accordingly resilience of the system. In this paper, Markov modeling technique is used to predict human behaviors patterns to distinguish between human anomalous behavior and system failure. The data is from the real experience of implementing innovative monitoring system in a five-star hotel which was part of the project of gamification for changing guests’ behavior. The idea was to develop Resilience Supported System to decrease the fault error and alarms and to increase the reliability and resilience of the system.

Resilience Supported System for Innovative Water Monitoring Technology from Koorosh Aslansefat

]]> 80 3 https://cdn.slidesharecdn.com/ss_thumbnails/03resiliencesupportedsystem-180503140313-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 A Novel Extended Adaptive Thresholding for Industrial Alarm Systems /slideshow/a-novel-extended-adaptive-thresholding-for-industrial-alarm-systems/75810082 v4anovelextendedadaptivethresholding-170509095616
Decision-making systems are known as the main pillar of industrial alarm systems, and they can directly effect on system’s performance. It is evident that because of hidden attributes in the measurements such as correlation and nonlinearity, thresholding systems faced wrong separation defining by Missed Alarm Rate (MAR) and False Alarm Rate (FAR). This study introduced a novel extended adaptive thresholding based on mean-change point detection algorithm and shows that it is more efficient than other existing thresholding algorithm in the literature. Number hypothetical and industrial examples are given to delineate the capabilities and limitation of proposed method and prove its effectiveness in an industrial alarm system.]]>
Decision-making systems are known as the main pillar of industrial alarm systems, and they can directly effect on system’s performance. It is evident that because of hidden attributes in the measurements such as correlation and nonlinearity, thresholding systems faced wrong separation defining by Missed Alarm Rate (MAR) and False Alarm Rate (FAR). This study introduced a novel extended adaptive thresholding based on mean-change point detection algorithm and shows that it is more efficient than other existing thresholding algorithm in the literature. Number hypothetical and industrial examples are given to delineate the capabilities and limitation of proposed method and prove its effectiveness in an industrial alarm system.]]> Tue, 09 May 2017 09:56:16 GMT /slideshow/a-novel-extended-adaptive-thresholding-for-industrial-alarm-systems/75810082 KooroshAslansefat@slideshare.net(KooroshAslansefat) A Novel Extended Adaptive Thresholding for Industrial Alarm Systems KooroshAslansefat Decision-making systems are known as the main pillar of industrial alarm systems, and they can directly effect on system’s performance. It is evident that because of hidden attributes in the measurements such as correlation and nonlinearity, thresholding systems faced wrong separation defining by Missed Alarm Rate (MAR) and False Alarm Rate (FAR). This study introduced a novel extended adaptive thresholding based on mean-change point detection algorithm and shows that it is more efficient than other existing thresholding algorithm in the literature. Number hypothetical and industrial examples are given to delineate the capabilities and limitation of proposed method and prove its effectiveness in an industrial alarm system. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/v4anovelextendedadaptivethresholding-170509095616-thumbnail.jpg?width=120&height=120&fit=bounds" /> Decision-making systems are known as the main pillar of industrial alarm systems, and they can directly effect on system’s performance. It is evident that because of hidden attributes in the measurements such as correlation and nonlinearity, thresholding systems faced wrong separation defining by Missed Alarm Rate (MAR) and False Alarm Rate (FAR). This study introduced a novel extended adaptive thresholding based on mean-change point detection algorithm and shows that it is more efficient than other existing thresholding algorithm in the literature. Number hypothetical and industrial examples are given to delineate the capabilities and limitation of proposed method and prove its effectiveness in an industrial alarm system.

A Novel Extended Adaptive Thresholding for Industrial Alarm Systems from Koorosh Aslansefat

]]> 146 2 https://cdn.slidesharecdn.com/ss_thumbnails/v4anovelextendedadaptivethresholding-170509095616-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 A Strategy for Reliability Evaluation and Fault Diagnosis of Autonomous Underwater Gliding Robot based on its Fault Tree /slideshow/a-strategy-for-reliability-evaluation-and-fault-diagnosis-of-autonomous-underwater-gliding-robot-based-on-its-fault-tree/44506792 icracepresentation-150210110414-conversion-gate01
Underwater vehicles contribute significantly to exploiting great maritime resources. Autonomous vehicles are one of the various kinds of underwater vehicles which are able to perform operations without operator's interference. Autonomous underwater vehicles can be classified according to their propulsion systems. Autonomous Underwater Gliders (AUG) are among autonomous underwater vehicles which fall under the category of glide type underwater vehicles. They are designed in a way that they benefit low energy consumption and a wide survey range. Their reliable design is one of the challenges facing their manufacturing. Fault tolerance is one of the important attributes in designing reliable systems. Recognizing, evaluating and facing the faults are of great importance in designing fault tolerant systems. This paper studies underwater Glider vehicles' subsystems, considers their faults and causes, and provides a typical fault tree for these vehicles form which glider reliability and the effects of glider subsystems on its failure can be driven.]]>
Underwater vehicles contribute significantly to exploiting great maritime resources. Autonomous vehicles are one of the various kinds of underwater vehicles which are able to perform operations without operator's interference. Autonomous underwater vehicles can be classified according to their propulsion systems. Autonomous Underwater Gliders (AUG) are among autonomous underwater vehicles which fall under the category of glide type underwater vehicles. They are designed in a way that they benefit low energy consumption and a wide survey range. Their reliable design is one of the challenges facing their manufacturing. Fault tolerance is one of the important attributes in designing reliable systems. Recognizing, evaluating and facing the faults are of great importance in designing fault tolerant systems. This paper studies underwater Glider vehicles' subsystems, considers their faults and causes, and provides a typical fault tree for these vehicles form which glider reliability and the effects of glider subsystems on its failure can be driven.]]> Tue, 10 Feb 2015 11:04:14 GMT /slideshow/a-strategy-for-reliability-evaluation-and-fault-diagnosis-of-autonomous-underwater-gliding-robot-based-on-its-fault-tree/44506792 KooroshAslansefat@slideshare.net(KooroshAslansefat) A Strategy for Reliability Evaluation and Fault Diagnosis of Autonomous Underwater Gliding Robot based on its Fault Tree KooroshAslansefat Underwater vehicles contribute significantly to exploiting great maritime resources. Autonomous vehicles are one of the various kinds of underwater vehicles which are able to perform operations without operator's interference. Autonomous underwater vehicles can be classified according to their propulsion systems. Autonomous Underwater Gliders (AUG) are among autonomous underwater vehicles which fall under the category of glide type underwater vehicles. They are designed in a way that they benefit low energy consumption and a wide survey range. Their reliable design is one of the challenges facing their manufacturing. Fault tolerance is one of the important attributes in designing reliable systems. Recognizing, evaluating and facing the faults are of great importance in designing fault tolerant systems. This paper studies underwater Glider vehicles' subsystems, considers their faults and causes, and provides a typical fault tree for these vehicles form which glider reliability and the effects of glider subsystems on its failure can be driven. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/icracepresentation-150210110414-conversion-gate01-thumbnail.jpg?width=120&height=120&fit=bounds" /> Underwater vehicles contribute significantly to exploiting great maritime resources. Autonomous vehicles are one of the various kinds of underwater vehicles which are able to perform operations without operator's interference. Autonomous underwater vehicles can be classified according to their propulsion systems. Autonomous Underwater Gliders (AUG) are among autonomous underwater vehicles which fall under the category of glide type underwater vehicles. They are designed in a way that they benefit low energy consumption and a wide survey range. Their reliable design is one of the challenges facing their manufacturing. Fault tolerance is one of the important attributes in designing reliable systems. Recognizing, evaluating and facing the faults are of great importance in designing fault tolerant systems. This paper studies underwater Glider vehicles' subsystems, considers their faults and causes, and provides a typical fault tree for these vehicles form which glider reliability and the effects of glider subsystems on its failure can be driven.

A Strategy for Reliability Evaluation and Fault Diagnosis of Autonomous Underwater Gliding Robot based on its Fault Tree from Koorosh Aslansefat

]]> 2511 10 https://cdn.slidesharecdn.com/ss_thumbnails/icracepresentation-150210110414-conversion-gate01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 https://cdn.slidesharecdn.com/profile-photo-KooroshAslansefat-48x48.jpg?cb=1710066193 Koorosh Aslansefat was born in Tehran, Iran, in 1989. He received a BSc in Marine Electronic and Communication Engineering from Chabahar Maritime University, Chabahar, Iran in 2011 and ranked 1st among BSc students of the Electronic department. He is currently MSc student in Control Engineering at Shahid Beheshti University, Tehran, Iran. In his MSc studies, His main research interests are in Artificial Intelligent, Optimization with Evolutionary Methods, Markov Modelling, Risk Management, and Design High-reliable systems. www.koorosh-aslansefat.ir https://cdn.slidesharecdn.com/ss_thumbnails/safemlimbsav2-200916101253-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/safeml-safety-monitoring-of-machine-learning-classifiers-through-statistical-difference-measure/238508622 SafeML: Safety Monitor... https://cdn.slidesharecdn.com/ss_thumbnails/reliabilityevaluationofreconfigurablenmrarchitecturesupportedwithhotstandbysparemarkovmodelingandfor-200916100924-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/reliability-evaluation-of-reconfigurable-nmr-architecture-supported-with-hot-standby-spare-markov-modeling-and-formulation/238508532 Reliability Evaluation... https://cdn.slidesharecdn.com/ss_thumbnails/aconceptualframeworktoincorporatecomplex-191121122402-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/a-conceptual-framework-to-incorporate-complex-basic-events-in-hiphops/196011710 A Conceptual Framework...