Real-Time and Data-Driven Operation Optimization and Knowledge Discovery for an Enterprise Information System

An enterprise information system (EIS) is an integrated data-applications platform characterized by diverse, heterogeneous, and distributed data sources. For many enterprises, a number of business processes still depend heavily on static rule-based methods and extensive human expertise. Enterprises are faced with the need for optimizing operation scheduling, improving resource utilization, discovering useful knowledge, and making data-driven decisions.

This thesis research is focused on real-time optimization and knowledge discovery that addresses workflow optimization, resource allocation, as well as data-driven predictions of process-execution times, order fulfillment, and enterprise service-level performance. In contrast to prior work on data analytics techniques for enterprise performance optimization, the emphasis here is on realizing scalable and real-time enterprise intelligence based on a combination of heterogeneous system simulation, combinatorial optimization, machine-learning algorithms, and statistical methods.

On-demand digital-print service is a representative enterprise requiring a powerful EIS.We use real-life data from Reischling Press, Inc. (RPI), a digit-print-service provider (PSP), to evaluate our optimization algorithms.

In order to handle the increase in volume and diversity of demands, we first present a high-performance, scalable, and real-time production scheduling algorithm for production automation based on an incremental genetic algorithm (IGA). The objective of this algorithm is to optimize the order dispatching sequence and balance resource utilization. Compared to prior work, this solution is scalable for a high volume of orders and it provides fast scheduling solutions for orders that require complex fulfillment procedures. Experimental results highlight its potential benefit in reducing production inefficiencies and enhancing the productivity of an enterprise.

We next discuss analysis and prediction of different attributes involved in hierarchical components of an enterprise. We start from a study of the fundamental processes related to real-time prediction. Our process-execution time and process status prediction models integrate statistical methods with machine-learning algorithms. In addition to improved prediction accuracy compared to stand-alone machine-learning algorithms, it also performs a probabilistic estimation of the predicted status. An order generally consists of multiple series and parallel processes. We next introduce an order-fulfillment prediction model that combines advantages of multiple classification models by incorporating flexible decision-integration mechanisms. Experimental results show that adopting due dates recommended by the model can significantly reduce enterprise late-delivery ratio. Finally, we investigate service-level attributes that reflect the overall performance of an enterprise. We analyze and decompose time-series data into different components according to their hierarchical periodic nature, perform correlation analysis,

and develop univariate prediction models for each component as well as multivariate models for correlated components. Predictions for the original time series are aggregated from the predictions of its components. In addition to a significant increase in mid-term prediction accuracy, this distributed modeling strategy also improves short-term time-series prediction accuracy.

In summary, this thesis research has led to a set of characterization, optimization, and prediction tools for an EIS to derive insightful knowledge from data and use them as guidance for production management. It is expected to provide solutions for enterprises to increase reconfigurability, accomplish more automated procedures, and obtain data-driven recommendations or effective decisions.

Post-cesarean Section Peritonitis at a Referral Hospital in Rwanda: Factors Associated with Maternal Morbidity and Mortality

Background: Post-cesarean section peritonitis is the leading cause of maternal morbidity and mortality at the main referral hospital in Rwanda. Published data on the management of post-cesarean section peritonitis is limited. This study examined predictors of maternal morbidity and mortality for post-cesarean peritonitis.

Methods: We performed a prospective observational cohort study at the University Teaching Hospital Kigali (CHUK) from January 1 until December 31 2015, followed by a retrospective chart review of all subjects with post-cesarean section peritonitis admitted to CHUK from January 1 until December 31, 2014. All patients admitted with the diagnosis of post-cesarean section peritonitis undergoing exploratory laparotomy at CHUK were enrolled. Patients were followed to either discharge or death. Study variables included baseline demographic/clinical characteristics, admission physical exam, intraoperative findings, and management. Data were analyzed using STATA version 14.

Results: Of the 167 patients enrolled, 81 survived without requiring hysterectomy (49%), 49 survived requiring hysterectomy (29%), and 36 died (22%). In the multivariate analysis, severe sepsis was the most significant predictor of mortality (RR=4.0 [2.2-7.7]) and uterine necrosis was the most significant predictor of hysterectomy (RR=6.3 [1.6-25.2]). There were high rates of antimicrobial resistance (AMR) among the bacterial isolates cultured from intra-abdominal pus, with 52% of bacteria resistant to third-generation cephalosporins.

Conclusions: Post-cesarean section peritonitis carries a high mortality rate in Rwanda. It is also associated with a high rate of hysterectomy. Understanding the disease process and identifying factors associated with outcomes can help guide management during admission.