Journal of Innovations in Computer Science and Engineering (JICSE)

Abstract Understanding dynamic systems like disease outbreaks, social influence, and information diffusion requires effective modeling of complex networks. Traditional evaluation methods for static networks often fall short when applied to temporal networks. This paper introduces DGSP-GCN (Dynamic Graph Similarity Prediction based on Graph Convolutional Network), a deep learning-based framework that integrates graph convolutional networks with dynamic graph signal processing techniques to provide a unified solution for evaluating generative models and detecting anomalies in dynamic networks. DGSP-GCN assesses how well a generated network snapshot matches the expected temporal evolution, incorporating an attention mechanism to improve embedding quality and capture dynamic structural changes. The approach was tested on five real-world datasets: WikiMath, Chickenpox, PedalMe, MontevideoBus, and MetraLa. Results show that DGSP-GCN outperforms baseline methods, such as time series regression and random similarity assignment, achieving the lowest error rates (MSE of 0.0645, MAE of 0.1781, RMSE of 0.2507). These findings highlight DGSP-GCN's effectiveness in evaluating and detecting anomalies in dynamic networks, offering valuable insights for network evolution and anomaly detection research.

Abstract Process mining is a new research area that bridges the gap between data science and process science. Among the subfields of process mining, predictive process monitoring aims to predict process features such as the next event, outcome, and remaining time. In recent years, increasing research has been conducted in the area of remaining time prediction.
In this paper, we present an interpretable method for remaining time prediction. Interpretability is an advantageous feature for a prediction method, because it provides the necessary advice and warnings to the organization’s experts during the process execution when it is used in a recommender system. In the proposed method, we utilize distance metric learning methods to develop a distance function for process events. The distance function can be used to find the most similar cases to the intended case, and then the remaining time of the similar cases is used as the indicator of the remaining time of the intended case. Our proposed method has been evaluated on three datasets, and the evaluations revealed that it significantly outperforms the state-of-the-art baseline in two datasets while achieving comparable accuracy in the third dataset. Additionally, our proposed method provides interpretation, while the competitor methods are not interpretable.