This study applies MTAD-GAT to early anomaly detection in unmanned aerial vehicle (UAV) flight telemetry using the ALFA fault dataset. Thirty-one telemetry variables are arranged as lookback windows, and a graph-attention architecture is used to jointly model inter-feature relationships and temporal dependencies. To keep the evaluation compact, we rely on three indicators: PR-AUC for timestep-level anomaly ranking, Flight AUROC for flight-level fault separation, and mean time-to-detection (TTD) for early-warning capability. Under the operational setting, MTAD-GAT achieves a PR-AUC of 0.5282, a Flight AUROC of 0.8889, and a mean TTD of 15.13 timesteps. The same setting also records the highest PR-AUC among the conventional unsupervised baselines, indicating that jointly modeling feature interactions and temporal context is beneficial for UAV fault detection. The contribution of this work is to reframe UAV anomaly detection not only as a timestep-level scoring task but also as a flight-level early-warning problem.

Abstract
1. 서 론
2. 연구 방법
    2.1 데이터셋 구성 및 문제 정의
    2.2 데이터 전처리 및 입력 구성
    2.3 MTAD-GAT 기반 이상탐지 모델
    2.4 실험 조건 및 평가 지표
3. 실험 결과 및 고찰
    3.1 기존 비지도 이상탐지 기법과의 비교
    3.2  값 변경에 따른 MTAD-GAT 성능
    3.3 self_weight 변경에 따른 성능
    3.4 정규화 방식에 따른 성능 변화
    3.5 종합 고찰 및 한계점
4. 결 론
References

• 양은석(Aviation Team 2 at the Defense Agency for Technology and Quality (DTaQ), Korea.) | Eunsuk Yang Corresponding author