Structural Convergence of Maritime AIS and Financial Order-Flow Anomaly Detection: A Unified Telemetry Time-Series Framework for Cross-Domain Behavioral Pattern Recognition

Read full text Summarise with VIRAT
Authors: Anil Kumar Sharma
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

We present a formal proof that maritime Automatic Identification System (AIS) anomaly detection and financial options order-flow anomaly detection — systems built independently for entirely different domains — are structurally identical algorithms operating on different signal vocabularies. Both reduce to the same abstract primitive: a multi-condition sliding-window telemetry classifier with domain-specific false-positive filters and ratio-based confidence scoring. We specify this primitive formally as the ANKR Telemetry Anomaly Classifier (TAC) and demonstrate that the AIS-based maritime behavioral detection system (RepoEx/VMS, five-condition bitmask) and the Vyomo options trap detector (three-condition classifier) are direct instantiations differing only in signal domain, condition set, and threshold parameters. We further prove that the same framework extends without modification to medical vital-sign telemetry, IoT sensor anomaly networks, and satellite imagery change detection. The false-positive filter taxonomy — domain-specific noise categorization that suppresses known-benign signal patterns — is identified as the most novel transferable contribution, converting an alert-fatigued system into a precise one. The convergence result has significant intellectual property implications: a single unified patent specification covers all six identified domain instantiations rather than requiring separate filings per domain. The bitmask confidence encoding (conditions\_met / |C|) maps directly to the ANKR Trust Bitmask IP portfolio, creating cross-portfolio coherence. This defensive publication establishes priority for all six novel contributions listed herein.

Fields of Study & Subjects

Anomaly Detection Techniques and Applications Network Security and Intrusion Detection Software System Performance and Reliability

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
25 March 2026
Language
EN
Document type
Preprint