Event Tracking for Real-Time Unaware Sensitivity Analysis (EventTracker)

Abstract

Abstract-This paper introduces a platform for online Sensitivity Analysis (SA) that is applicable in large scale real-time data acquisition (DAQ) systems. Here we use the term real-time in the context of a system that has to respond to externally generated input stimuli within a finite and specified period. Complex industrial systems such as manufacturing, healthcare, transport, and finance require high quality information on which to base timely responses to events occurring in their volatile environments. The motivation for the proposed EventTracker platform is the assumption that modern industrial systems are able to capture data in real-time and have the necessary technological flexibility to adjust to changing system requirements. The flexibility to adapt can only be assured if data is succinctly interpreted and translated into corrective actions in a timely manner. An important factor that facilitates data interpretation and information modelling is an appreciation of the affect system inputs have on each output at the time of occurrence. Many existing sensitivity analysis methods appear to hamper efficient and timely analysis due to a reliance on historical data, or sluggishness in providing a timely solution that would be of use in real-time applications. This inefficiency is further compounded by computational limitations and the complexity of some existing models.In dealing with real-time event driven systems, the underpinning logic of the proposed method is based on the assumption that in the vast majority of cases changes in input variables will trigger events. Every single or combination of events could subsequently result in a change to the system state. The proposed event tracking sensitivity analysis method describes variables and the system state as a collection of events. The higher the numeric occurrence of an input variable at the trigger level during an event monitoring interval, the greater is its impact on the final analysis of the system state.Experiments were designed to compare the proposed event tracking sensitivity analysis method with a comparable method (that of Entropy). An improvement of 10% in computational efficiency without loss in accuracy was observed. The comparison also showed that the time taken to perform the sensitivity analysis was 0.5% of that required when using the comparable Entropy based method. ATA acquisition systems that deal with large quantities of input variables and have higher sampling frequencies result in high bandwidth communication and place a heavy computational load on the higher tier data processing and information systems within their hierarchy. The focus of researchers and practitioners in this area has been to minimize this computational overhead by eliminating input variables that have the least impact on the system, this so called sensitivity analysis is discussed in [1]- [6]. Sensitivity analysis techniques help system analysts to focus on the most valuable information, information that most significantly impacts on system behaviour. Sensitivit...

EventClustering for improved real time input variable selection and data modelling

“…We use the term real-time in the context of a system that has to respond to externally generated input stimuli within a finite and specified period [1]. At present to the best knowledge of the authors, besides the research papers published by the authors in real-time event-tracking and clustering [1] [15], there is no real-time system that creates a causal interrelationship of events for modelling purposes.…”

“…The basic parameters of the proposed event clustering methods are borrowed from [1]. A quick cross reference is necessary.…”

“…The cut-off threshold is a mechanism to deduct the less important input variables [1]. A false negative test is conducted to ensure the inputs are not unnecessarily discounted.…”

“…Therefore, the cause-effect relationship between the input variables and performance parameters generate the knowledge about the system. Minimizing cost of system by eliminating input variables that have the least impact on the system is named Sensitivity analysis (SA) [1][2][3][4]. The data filtering and sensitivity analysis techniques need to measure of the true impact of each system's input on the each output, however, due to the uncertainties of such relationships finding a true representation is challenging.…”

Simulation-based real-time performance monitoring (simmon): A platform for manufacturing and healthcare systems

“…The proposed EventTracker (Tavakoli and Mousavi 2011) is therefore tasked to enable complex event processing in real-time. EventTracker is an event-driven sensitivity analysis method that captures and interprets events as they occur.…”