Ordinal Decision-Tree-Based Ensemble Approaches: The Case of Controlling the Daily Local Growth Rate of the COVID-19 Epidemic

Abstract

In this research, we develop ordinal decision-tree-based ensemble approaches in which an objective-based information gain measure is used to select the classifying attributes. We demonstrate the applicability of the approaches using AdaBoost and random forest algorithms for the task of classifying the regional daily growth factor of the spread of an epidemic based on a variety of explanatory factors. In such an application, some of the potential classification errors could have critical consequences. The classification tool will enable the spread of the epidemic to be tracked and controlled by yielding insights regarding the relationship between local containment measures and the daily growth factor. In order to benefit maximally from a variety of ordinal and non-ordinal algorithms, we also propose an ensemble majority voting approach to combine different algorithms into one model, thereby leveraging the strengths of each algorithm. We perform experiments in which the task is to classify the daily COVID-19 growth rate factor based on environmental factors and containment measures for 19 regions of Italy. We demonstrate that the ordinal algorithms outperform their non-ordinal counterparts with improvements in the range of 6–25% for a variety of common performance indices. The majority voting approach that combines ordinal and non-ordinal models yields a further improvement of between 3% and 10%.

Performance evaluation of selected decision tree algorithms for COVID-19 diagnosis using routine clinical data

“…Health care industries all over the world have employed various technological innovations, such as ML-based artificial intelligence (AI) solution, to fight against COVID-19 ( 29 ). Predictive models based on ML for mining datasets can greatly contribute to recognizing high-risk groups, early detection of disease, and adoption of effective treatment plans ( 18 , 30 ). This led to reducing uncertainty and ambiguity by offering evidence-based medicine for risk analysis, prediction, and treatment ( 11 ).…”

“…The use of DT-based ML algorithms (Learning trees) is proven to be useful for optimal infectious disease prediction and diagnosis ( 30 , 31 ). This led to reducing uncertainty and ambiguity by offering evidence-based medicine for risk analysis, prediction, and care plans ( 32 ).…”

A smart process controller framework for Industry 4.0 settings

“…9 Control and awareness and process-diagnosis modules of the smart controller in a silicon wafers manufacturing process with a desired thickness lead to deterioration of the polishing velocity that resulted in high thickness wafers, using machine learning algorithms. In our showcase, we would use an ordinal decision tree algorithm (Singer and Marudi 2020; to apply root cause analysis as a way of identifying which parameters may be influencing the levels of velocity intensity (i.e., low velocity, medium velocity, high velocity, very high velocity). This ordinal machine learning algorithm is suitable for the process-diagnosis module in our example, for two main reasons.…”

Mesoscopic Modeling and Rapid Simulation of Incremental Changes in Epidemic Scenarios

“…Therefore, a mesoscopic simulation approach is described that offers the potential to serve as a continuum from macroscopic to microscopic levels, whose configurations can be customized based on data availability, desired modeling accuracy, targeted level of behavioral detail, and other such factors. Building over this mesoscopic framework, an incremental simulation approach based on what-if tree evolution is presented that offers new scaling capabilities that were not possible before in rapidly simulating thousands or millions of incrementally-varied scenarios over a large domain of a base simulation [2,25,26]. The mesoscopic model can be used in the incremental what-if tree evaluation on state-of-the-art accelerated computing platforms including supercomputers that offer thousands of GPUs, and effectively exploit the singleinstruction-multiple-data (SIMD) mode of high-performance parallel computing.…”