کنفرانس بین المللی کنترل ، ابزار دقیق و اتوماسیون

صفحه اصلی / نهمین کنفرانس بین المللی کنترل ، ابزار دقیق و اتوماسیون

Attention and Autoencoder Hybrid Model for Unsupervised Online Anomaly Detection

نویسندگان :

Seyed Amirhossein Najafi¹ Mohammad Hassan Asemani² Peyman Setoodeh³

1- دانشگاه شیراز 2- دانشگاه شیراز 3- دانشگاه شیراز

کلمات کلیدی :

Autoencoder،Online Anomaly Detection،Time Series،Transformer،Unsupervised Learning

چکیده :

This paper introduces a hybrid attention and autoencoder (AE) model for unsupervised online anomaly detection in time series. The autoencoder captures local structural patterns in short embeddings, while the attention model learns long-term features, facilitating parallel computing with positional encoding. Unique in its approach, our proposed hybrid model combines attention and autoencoder for the first time in time series anomaly detection. It employs an attention-based mechanism, akin to the deep transformer model, with key architectural modifications for predicting the next time step window in the autoencoder's latent space. The model utilizes a threshold from the validation dataset for anomaly detection and introduces an alternative method based on analyzing the first statistical moment of error, improving accuracy without dependence on a validation dataset. Evaluation on diverse real-world benchmark datasets and comparing with other well-established models, confirms the effectiveness of our proposed model in anomaly detection.

لیست مقالات

لیست مقالات بایگانی شده

Practical and Applied Control Tutorial: Employing Simulink to Master Theoretical Concepts

Mohammad Afkar - Roghayeh Gavagsaz-Ghoachani - Matheepot Phattanasak - Serge Pierfederici

Design and Implementation of an Automated CO2 Incubator for Cell Culture Applications

Mohammad Sadegh Bank - Fateme Khanmohammadi - Seyed Ahmadreza Firoozabadi - Majid Badieirostami

OPC UA Over TSN (Time Sensitive Network) for Vertical and Machine to Machine Communication

Abdollah Moshiri - Ali Mohammad Afshin Hemmatyar

Texture Analysis of Corn-based Snacks with Fast Fourier Transform

José-David Martínez-Velasco - Annamaría Filomena-Ambrosio - Claudia L. Garzón-Castro - Julieta Domínguez-Soberanes - Paolo Visconti - Ramiro Velázquez

Detection of Defective Products in Injection Molding Process Using YOLO-NAS

Mohammadreza Asadi - Seyedeh Sogand Hashemi - Mohammad Taghi Sadeghi

یک روش یادگیری عمیق با نظارت مبتنی بر حافظه طولانی کوتاه مدت برای مدلسازی حسگر های نرم

شیدک یزدانی - سید جلیل ساداتی رستمی - سپیده عیسی‌پور

Frequency Regulation Improvement in AC Microgrids: A Fuzzy-Based Extended Virtual Synchronous Generator Control

Arman Jafari - Sharara Rehimi - Hassan Bevrani

Quantum Technology & Quantum Neural Networks in Smart Grids Control: Premier Perspectives

Ashkan Safari - Amir Ghavifekr

Disturbance Compensation for Bidirectional Half-bridge DC-DC Converter in a Hybrid Photovoltaic-Battery Energy System: An H-based Approach

Fatemeh Esmaeili - Hamid Reza Koofigar

Medium-Term Load Forecasting of Iran Khodro Company using Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) Deep Neural Networks

Mahasta Pahlawan - Roohollah Barzamini - Seyyed Abolfazl Yasini

بیشتر

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.0.5