No abstract

Predictive process monitoring is concerned with the analysis of events produced during the execution of a business process in order to predict as early as possible the final outcome of an ongoing case. Traditionally, predictive process monitoring methods are optimized with respect to accuracy. However, in environments where users make decisions and take actions in response to the predictions they receive, it is equally important to optimize the stability of the successive predictions made for each case. To this end, this paper defines a notion of temporal stability for binary classification tasks in predictive process monitoring and evaluates existing methods with respect to both temporal stability and accuracy. We find that methods based on XGBoost and LSTM neural networks exhibit the highest temporal stability. We then show that temporal stability can be enhanced by hyperparameter-optimizing random forests and XGBoost classifiers with respect to inter-run stability. Finally, we show that time series smoothing techniques can further enhance temporal stability at the expense of slightly lower accuracy.

Alzheimer’s disease and other types of dementia are the top cause for disabilities in later life and various types of experiments have been performed to understand the underlying mechanisms of the disease with the aim of coming up with potential drug targets. These experiments have been carried out by scientists working in different domains such as proteomics, molecular biology, clinical diagnostics and genomics. The results of such experiments are stored in the databases designed for collecting data of similar types. However, in order to get a systematic view of the disease from these independent but complementary data sets, it is necessary to combine them. In this study we describe a heterogeneous network-based data set for Alzheimer’s disease (HENA). Additionally, we demonstrate the application of state-of-the-art graph convolutional networks, i.e. deep learning methods for the analysis of such large heterogeneous biological data sets. We expect HENA to allow scientists to explore and analyze their own results in the broader context of Alzheimer’s disease research.

Abstract-Model precision in a classification task is highly dependent on the feature space that is used to train the model. Moreover, whether the features are sequential or static will dictate which classification method can be applied as most of the machine learning algorithms are designed to deal with either one or another type of data. In real-life scenarios, however, it is often the case that both static and dynamic features are present, or can be extracted from the data. In this work, we demonstrate how generative models such as Hidden Markov Models (HMM) and Long Short-Term Memory (LSTM) artificial neural networks can be used to extract temporal information from the dynamic data. We explore how the extracted information can be combined with the static features in order to improve the classification performance. We evaluate the existing techniques and suggest a hybrid approach, which outperforms other methods on several public datasets.