Litcius/Paper detail

A hybrid approach of ConvLSTMBNN-DT and GPT-4 for real-time anomaly detection decision support in edge–cloud environments

Radityo Fajar Pamungkas, Ida Bagus Krishna Yoga Utama, Khairi Hindriyandhito, Yeong Min Jang

2024ICT Express13 citationsDOIOpen Access PDF

Abstract

Anomaly detection is a critical requirement across diverse domains to promptly identify abnormal behavior. Conventional approaches often face limitations with uninterpretable anomaly detection results, impeding efficient decision-making processes. This paper introduces a novel hybrid approach, the convolutional LSTM Bayesian neural network with nonparametric dynamic thresholding (ConvLSTMBNN-DT) for prediction-based anomaly detection. In addition, the model integrates fine-tuned generative pre-training version 4 (GPT-4) to provide human-interpretable explanations in edge–cloud environments. The proposed method demonstrates exceptional performance, achieving an average F1−score of 0.91 and an area under the receiver operating characteristic curve (AUC) of 0.86. Additionally, it effectively offers comprehensible decision-support explanations.

Topics & Concepts

Anomaly detectionAnomaly (physics)Computer scienceThresholdingEnhanced Data Rates for GSM EvolutionArtificial intelligenceReceiver operating characteristicConvolutional neural networkCloud computingMachine learningPattern recognition (psychology)Data miningImage (mathematics)PhysicsOperating systemCondensed matter physicsAnomaly Detection Techniques and ApplicationsNetwork Security and Intrusion DetectionTime Series Analysis and Forecasting