The predictive business process monitoring is a family of online approaches to predict the unfolding of running traces basedon the knowledge learned from historical event logs. In this paper, we address the task of predicting the next trace activity from the completed events in a running trace. This is an important business capability as counting on accurate predictions of the future activities may allow companies to guarantee the higher utilization by acting proactively in anticipation. We propose a novel predictive process approach that couples multi-view learning and deep learning, in order to gain predictive accuracy by accounting for the variety ofinformation possibly recorded in event logs. Experiments with various benchmark event logs prove the effectiveness of the proposed approach compared to several recent state-of-the-art methods.

The outcome-oriented predictive process monitoring is a family of predictive process mining techniques that have witnessed rapid development and increasing adoption in the past few years. Boosted by the recent successful applications of deep learning in predictive process mining, we propose ORANGE, a novel deep learning method for learning outcome-oriented predictive process models. The main innovation of this study is that we adopt an imagery representation of the ongoing traces, which delineates potential data patterns that arise at neighbour pixels. Leveraging a collection of images representing ongoing traces, we train a Convolutional Neural Network (CNN) to predict the outcome of an ongoing trace. The empirical study shows the feasibility of the proposed method by investigating its accuracy on different benchmark outcome prediction problems in comparison to state-of-art competitor methods. In addition, we show how ORANGE can be integrated as an Intelligent Assistant into a CVM realized by MTM Project srl company to support sales agents in their negotiations. This case study shows that ORANGE can be effectively used to smartly monitor the outcome of ongoing negotiations by early highlighting negotiations that are candidate to be completed successfully.

Conventional methods for measuring cardiovascular parameters use skin contact techniques requiring a measuring device to be worn by the user. To avoid discomfort of contact devices, camera-based techniques using photoplethysmography have been recently introduced. Nevertheless, these solutions are typically expensive and difficult to be used daily at home. In this work, we propose an innovative solution for monitoring cardiovascular parameters that is low cost and can be easily integrated within any common home environment. The proposed system is a contact-less device composed of a see-through mirror equipped with a camera that detects the person’s face and processes video frames using photoplethysmography in order to estimate the heart rate, the breath rate and the blood oxygen saturation. In addition, the color of lips is automatically detected via clustering-based color quantization. The estimated parameters are used to predict a risk of cardiovascular disease by means of fuzzy inference rules integrated in the mirror-based monitoring system. Comparing our system to a contact device in measuring vital parameters on still or slightly moving subjects, we achieve measurement errors that are within acceptable margins according to the literature. Moreover, in most cases, the response of the fuzzy rule-based system is comparable with that of the clinician in assessing a risk level of cardiovascular disease.

In this paper, we introduce PROPHET, an innovative approach to predictive process monitoring based on Heterogeneous Graph Neural Networks. PROPHET is designed to strike a balance between accurate predictions and interpretability, particularly focusing on the next-activity prediction task. For this purpose, we represent the event traces recorded for different business process executions as heterogeneous graphs within a multi-view learning scheme combined with a heterogeneous graph learning approach. Using heterogeneous Graph Attention Networks (GATs), we achieve good accuracy by incorporating different characteristics of several events into graphs with different node types and leveraging different types of graph links to express relationships between event characteristics, as well as relationships between events. In addition, the use of a GAT model enables the integration of a modified version of the GNN Explainer algorithm to add the explainable component to the predictive model. In particular, the GNN Explainer algorithm is modified to disclose explainable information related to characteristics, events and relationships between events that mainly influenced the prediction. Experiments with various benchmark event logs prove the accuracy of PROPHET compared to several current state-of-the-art methods and draw insights from explanations recovered through the GNN Explainer algorithm.