PurposeThe feasibility of process mining combined with simulation techniques in estimating the effectiveness of COVID-19 prevention strategies on infection and mortality trends to determine best practices is assessed in this study. The quarantine event log is built from the CUSP (the COVID-19 US State Policy) database, where the dates of implemented social policies in the USA to respond to the COVID-19 pandemic are documented.Design/methodology/approachCOVID-19 is a highly infectious disease leading to a very high death toll worldwide. In most countries, the governments have resorted to a series of drastic strategies to prevent the outbreak by restricting the activities and movement among their population for a predefined time. Heretofore, different approaches have been published to estimate quarantine strategies and the majority signify the positive effect on managing this pandemic. Notably, the process perspective of COVID-19 datasets is of less concern among researchers. The purpose of this paper is to exploit the process mining techniques to model and analyze the quarantine implementation processes.FindingsThe discovered process model has 51 process variants for 51 cases (states), which indicate the quarantine activities were executed in different orders and periods during the pandemic. The time interval analysis between activities reveals the states with the most extended quarantine periods. These primary process mining insights are applied to define scenarios and variables of an agent-based model. The simulation findings indicate a meaningful relation between enforcing quarantine strategies and a declining trend of infection by 90% in the case of following strict quarantine and mask mandates. It is observed that in the post-quarantine period, the disease repeats its ascending trend unless implementation of different intervention strategies likes vaccination.Originality/valueThis study is the first in introducing process mining techniques in analyzing the COVID-19 quarantine strategies impact. The findings provide valuable insights for policymakers to proper control strategies and the process mining research community in expanding more process-related analysis on this pandemic. Also, the results have broad implications for research in other fields like information science to estimate the impact of quarantine strategies on process patterns in library systems.
No abstract
Background: Though the process mining algorithms have evolved in the past decade, the lack of attention to extracting event logs from raw data of databases in an automatic manner is evident. These logs are available in a process-oriented manner in the process-aware information systems. Still, there are areas where their extraction is a challenge to address (e.g., trauma registries). Objective: The registry data are recorded manually and follow an unstructured ad-hoc pattern; prone to high noises and errors; consequently, registry logs are classified at a maturity level of one, and extracting process-centric information is not a trivial task therein. The experiences made during the event log building from the trauma registry are the subjects to be studied. Results: The result indicates that the three-phase self-service registry log builder tool can withstand the mentioned issues by filtering and enriching the raw data and making them ready for any level of process mining analysis. This proposed tool is demonstrated through process discovery in the National Trauma Registry of Iran, and the encountered challenges and limitations are reported. Conclusion: This tool is an interactive visual event log builder for trauma registry data and is freely available for studies involving other registries. In conclusion, future research directions derived from this case study are suggested.
Recommender systems have been widely applied in several domains to make informed decisions by recommending items that might be of interest. Considering recommendation during business process execution is also highly advantageous as the efficient suggestions about possible activities or resources can impact process performance. However, the deployment of the recommendation frameworks in process mining still needs more investigations to identify the current challenges to enable the practical application of research findings and ensure a large-scale adoption of this technique. Accordingly, a systematic review is conducted to provide a taxonomy of the published studies on process-aware recommender systems based on specified criteria, including the type and perspective of recommendation, a list of datasets and evaluation metrics used in the setting of PARS, implementation environments, and different algorithms used in PARS. In this regard, there are various insights extracted from this study: (i) Most studies in the business process analysis domain are of descriptive and predictive nature, (ii) recommendation in process mining is an emerging research area that is being evolving; the majority of proposals relate to 2015 and after that, and (iii) due to the lack of common evaluation protocol, datasets, and metrics, most studies are validated through experiments and prototyping, with less tendency to the practical implementation of a solution regarding real scenarios.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.