A neural network with the widely-used ReLU activation has been shown to partition the
sample space into many convex polytopes for prediction. However, the parameterized way a …

Abstract Industrial Control Systems encompass supervisory systems (SCADA) and cyber-
physical components (sensors/actuators), which are typically deployed in critical …

This paper provides an overview of anomaly detection in high-dimensional datasets,
addressing challenges such as the curse of dimensionality. It highlights preprocessing …

Artificial intelligence has prevailed in various scientific and engineering fields in recent
years. Its ability to learn from large data and make predictions based on learned patterns …

Anomaly detection problems are particularly important in various real-word contest such as
fraud detection, finance, intrusion detection and cyber-security. Several methods that are …

Anomaly detection plays a crucial role in safeguarding the safety and integrity of
pharmaceutical operations, where identifying potential risks like counterfeit drugs …