Process Mining of Programmable Logic Controllers: Input/Output Event Logs

Darabi

2019

IEEE Access

Self Cite

In complex processes, various events can happen in different sequences. The prediction of the next event given an a-priori process state is of importance in such processes. Recent methods have proposed deep learning techniques such as recurrent neural networks, developed on raw event logs, to predict the next event from a process state. However, such deep learning models by themselves lack a clear representation of the process states. At the same time, recent methods have neglected the time feature of event instances. In this paper, we take advantage of Petri nets as a powerful tool in modeling complex process behaviors considering time as an elemental variable. We propose an approach which starts from a Petri net process model constructed by a process mining algorithm. We enhance the Petri net model with time decay functions to create continuous process state samples. Finally, we use these samples in combination with discrete token movement counters and Petri net markings to train a deep learning model that predicts the next event. We demonstrate significant performance improvements and outperform the state-of-the-art methods on nine real-world benchmark event logs.

Section: Discussionmentioning

confidence: 99%

Decay Replay Mining to Predict Next Process Events

Darabi

2019

IEEE Access

Self Cite

“…Thus, AVATAR is a step forward towards reliably measuring generalization. Besides a novel perspective on the metric of generalization, SGANs enable other real-world applications in the domain of process mining, such as for the analysis of black-box controller and software as in [2], or to obtain robust and accurate simulation models.…”

Section: Discussionmentioning

confidence: 99%

“…The training and sampling have been performed on NVIDIA GeForce RTX 2080 GPUs and took 2-3 hours per extended RelGAN and dataset. 2 https://github.com/ProminentLab/AVATAR 2) Sampling Results Figure 3 visualizes the number of sampled variants, i.e. |V S |, tp, and tp u for each ground truth system and for each of the four P N and four GAN sampling approaches.…”

Section: Methodology Evaluation 1) Sgan Training and Samplingmentioning

confidence: 99%

“…Process mining is a comparatively young research discipline that delights itself on ever-increasing popularity with applications in multiple domains such as Healthcare [1], Manufacturing [2], Robotic Process Automation [3], Human-Computer Interaction [4], and Simulation [5]. Commonly, process mining techniques are leveraged to analyze a system.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adversarial System Variant Approximation to Quantify Process Model Generalization

Darabi

2020

IEEE Access

Self Cite

In process mining, process models are extracted from event logs using process discovery algorithms and are commonly assessed using multiple quality metrics. While the metrics that measure the relationship of an extracted process model to its event log are well-studied, quantifying the level by which a process model can describe the unobserved behavior of its underlying system falls short in the literature. In this paper, a novel deep learning-based methodology called Adversarial System Variant Approximation (AVATAR) is proposed to overcome this issue. Sequence Generative Adversarial Networks are trained on the variants contained in an event log with the intention to approximate the underlying variant distribution of the system behavior. Unobserved realistic variants are sampled either directly from the Sequence Generative Adversarial Network or by leveraging the Metropolis-Hastings algorithm. The degree by which a process model relates to its underlying unknown system behavior is then quantified based on the realistic observed and estimated unobserved variants using established process model quality metrics. Significant performance improvements in revealing realistic unobserved variants are demonstrated in a controlled experiment on 15 ground truth systems. Additionally, the proposed methodology is experimentally tested and evaluated to quantify the generalization of 60 discovered process models with respect to their systems.

“…Process mining is a comparatively young research discipline that aims to extract knowledge from such sequences. Applications of process mining can be found across many industries, mainly to analyze and optimize applied processes, such as in business process management [5], automation [6], [7], manufacturing [8], [9], and recently in healthcare [10], [11]. Healthcare organizations increasingly acknowledge process mining and the use of empirical data to improve processes [12].…”

Section: Introductionmentioning

confidence: 99%

Improving the In-Hospital Mortality Prediction of Diabetes ICU Patients Using a Process Mining/Deep Learning Architecture

IEEE J. Biomed. Health Inform.

Galanter

Boyd

et al. 2022

Self Cite

Diabetes intensive care unit (ICU) patients are at increased risk of complications leading to in-hospital mortality. Assessing the likelihood of death is a challenging and timeconsuming task due to a large number of influencing factors. Healthcare providers are interested in the detection of ICU patients at higher risk, such that risk factors can possibly be mitigated. While such severity scoring methods exist, they are commonly based on a snapshot of the health conditions of a patient during the ICU stay and do not specifically consider a patient's prior medical history. In this paper, a process mining/deep learning architecture is proposed to improve established severity scoring methods by incorporating the medical history of diabetes patients. First, health records of past hospital encounters are converted to event logs suitable for process mining. The event logs are then used to discover a process model that describes the past hospital encounters of patients. An adaptation of Decay Replay Mining is proposed to combine medical and demographic information with established severity scores to predict the inhospital mortality of diabetes ICU patients. Significant performance improvements are demonstrated compared to established risk severity scoring methods and machine learning approaches using the Medical Information Mart for Intensive Care III dataset.