Process mining techniques can extract process models from event logs produced by information systems. However, in flexible environments, simply using existing methods often leads to complex process models that are hard to understand, due to the less structured and greater complexity of processes in real life. Trace clustering is a pre-processing technique that enhances the effectiveness of model mining by partitioning similar behaviors in logs. In this paper, we present a Multi-view Trace Clustering method, named MTC, that improves the homogeneity of trace subclusters. Our method consists of three parts: (1) We use trace profiles to depict the traces from different views, and each profile would be transformed into a graph based on the k-nearest neighbor algorithm; (2) A fusion graph is designed to capture the information among these graphs based on an attention coefficient matrix, and then the graph convolutional networks are used to encode all graphs for obtaining the common representation; (3) We also enhance the characterization of the common representation with an inner decoder. Finally, we adopt k-means to cluster the traces in the log based on the common representation. Extensive experiments using multiple datasets illustrate that MTC significantly surpasses state-of-the-art trace clustering methods

Process-aware information systems (PAIS) are designed to manage and support business processes within an organization. Drift detection in process mining aims to detect process changes by analyzing event logs, which can guarantee the accuracy and reliability of business processes within PAIS. However, existing methods often only consider process changes from a single perspective (e.g., control-flow), without fully utilizing other information in event logs like resources and timestamps. In this paper, we propose a novel Multi-view Drift Detection method, called MDD, to detect changes with graph convolutional networks. Specifically, 1) multiple k-nearest neighbors graphs are constructed for two log segments based on multiple perspectives, and graph convolutional networks are employed to capture features from these graphs. Meanwhile, we utilize a fully connected network to fuse multiple knn graphs, generating two fusion graphs; 2) we use Wasserstein distance to measure the distance between two fusion graphs after feature fusion; 3) the K-means algorithm is adopted to find the candidate drift points, and then the actual change points will be identified with a filter mechanism. Experimental results demonstrate that the MDD effectively identifies drift points on simulated logs and real-life logs.

The proliferation of wireless sensors enables the effective collection of human behavior trajectories, especially in the smart home domain. Studying human behavior patterns can not only improve the design of products and services but also assist healthcare professionals in better managing and treating illnesses. However, existing research on human behavior patterns suffers from non-visualization of the analysis process and time-consuming issues. In this paper, we employ graph convolutional neural networks for the analysis of human behavior patterns based on PIR sensor networks. Specifically, 1) we preprocess the human location data collected by sensors and create a directed graph that visually represents the movement of people within their homes; 2) we use graph convolutional networks to extract features from each graph and incorporate the time proportion of each room into the features to enhance the clustering accuracy; 3) we utilize the K-Means algorithm to cluster different directed graphs, and present distinct behavior patterns of individuals during different time intervals in a calendar format for clear visualization. The experiments demonstrate that our method effectively distinguishes between different human behavior patterns indoors, allowing to us detect patterns happening on special days.