D2H-AD: A Hybrid Model Utilizing Hyperdimensional Computing for Advanced Anomaly Detection

2026-06-11

AI Summary

This work addresses the limitations of traditional anomaly detection methods, which often require extensive labeled data, incur high computational costs, and exhibit poor scalability on edge devices and in high-dimensional settings. The authors propose D2H-AD, a novel framework that, for the first time, jointly embeds density and distance information into a hypervector space. By integrating density-distance hybrid encoding with binary high-dimensional representations, D2H-AD enables lightweight, efficient, and interpretable anomaly characterization within a unified architecture. Evaluated on five benchmark datasets, the method consistently outperforms baseline approaches—including HDAD, ODHD, and One-Class SVM—in both F1-score and ROC-AUC, demonstrating strong resilience to class imbalance and noise, as well as low inference latency, making it well-suited for TinyML and edge AI deployment.

Abstract

Anomaly detection is a fundamental component of intelligent systems with applications in healthcare, cybersecurity, smart grids, and IoT environments. Although conventional machine learning and deep learning methods have demonstrated effectiveness in identifying anomalies, they often rely on large labeled datasets, incur high computational costs, and face scalability challenges in edge and high-dimensional settings. This paper presents D2H-AD, a novel anomaly detection framework based on Hyperdimensional Computing (HDC), a brain-inspired paradigm that represents information using high-dimensional distributed vectors. Unlike existing HDC-based methods, D2H-AD integrates distance-based similarity and density-aware encoding within a unified framework, improving anomaly representation and detection performance. Ablation studies show that hyperdimensional encoding alone yields up to 5.4% higher ROC-AUC than applying the same density-distance scoring directly in the original feature space. Furthermore, D2H-AD consistently outperforms five established baselines, namely HDAD, ODHD, One-Class SVM, Isolation Forest, and Autoencoders, across all evaluated datasets. The framework is lightweight, interpretable, and computationally efficient, making it suitable for resource-constrained and real-time applications. We validate D2H-AD on five benchmark datasets and demonstrate superior F1-score and ROC-AUC performance, together with robustness to class imbalance, noise, and data complexity. In addition to improved accuracy, D2H-AD offers scalability, a small memory footprint, and low-latency operation enabled by binary computations and a compact design. These properties make it particularly attractive for TinyML and edge AI deployments. The proposed framework highlights the potential of HDC for accurate, interpretable, and energy-efficient anomaly detection in dynamic environments.

Problem

• anomaly detection
• hyperdimensional computing
• edge AI
• scalability
• computational efficiency

Innovation

• Hyperdimensional Computing
• Anomaly Detection
• Density-aware Encoding
• Edge AI
• TinyML