Results 51 to 60 of about 13,859 (190)

Transformer-based autoencoder with ID constraint for unsupervised anomalous sound detection

EURASIP Journal on Audio, Speech, and Music Processing, 2023
Unsupervised anomalous sound detection (ASD) aims to detect unknown anomalous sounds of devices when only normal sound data is available. The autoencoder (AE) and self-supervised learning based methods are two mainstream methods.
Jian Guan, Youde Liu, Qiuqiang Kong, Feiyang Xiao, Qiaoxi Zhu, Jiantong Tian, Wenwu Wang   +6 more
doaj   +1 more source

A Survey for Deep Reinforcement Learning Based Network Intrusion Detection

Applied AI Letters, Volume 7, Issue 2, June 2026.
This paper surveys deep reinforcement learning (DRL) for network intrusion detection, evaluating model efficiency, minority attack detection, and dataset imbalance. Findings show DRL achieves state‐of‐the‐art results on public datasets, sometimes surpassing traditional deep learning.
Wanrong Yang, Alberto Acuto, Yihang Zhou, Dominik Wojtczak   +3 more
wiley   +1 more source

Diffusional magnetic resonance imaging anonymizing with variational autoencoder

Quantitative Biology, Volume 14, Issue 2, June 2026.
Abstract Anonymization is a crucial de‐identification technique that protects data privacy while ensuring its utility for model building. Current generative models such as generative adversarial networks and variational auto‐encoders (VAEs) have been applied to medical image anonymization but mainly focus on general image features, lacking specificity ...
Yunheng Shen, Ling Zheng, Ruohan Liu, Haoran Feng, Hairong Lv   +4 more
wiley   +1 more source

SVD-AE: Simple Autoencoders for Collaborative Filtering

Accepted by IJCAI ...
Hong, Seoyoung, Choi, Jeongwhan, Lee, Yeon-Chang, Kumar, Srijan, Park, Noseong   +4 more
openaire   +2 more sources

Graph Neural Network in Raman Spectroscopy to Leverage the Performance and Interpretability of the Classification

Chemistry–Methods, Volume 6, Issue 5, May 2026.
Graphic neural networks are constructed for Raman‐based biomedical applications after transferring Raman spectra into graph representations, i.e., nodes and edges. The classification is observed to provide better robustness against disturbing spectral variations such as device‐to‐device differences.
Shuxia Guo, Sandra Baaba Frempong, Markus Salbreiter, Annette Wagenhaus, Petra Rösch, Jürgen Popp, Thomas Bocklitz   +6 more
wiley   +1 more source

A model‐driven robust deep learning wireless transceiver

IET Communications, 2021
Recently, deep learning (DL) has been successfully applied in computer vision and natural language processing. The communication physical layer based on deep learning has received widespread attention.
Sirui Duan, Jingyi Xiang, Xiang Yu
doaj   +1 more source

AE SemRL: Learning Semantic Association Rules with Autoencoders

Association Rule Mining (ARM) is the task of learning associations among data features in the form of logical rules. Mining association rules from high-dimensional numerical data, for example, time series data from a large number of sensors in a smart environment, is a computationally intensive task.
Karabulut, Erkan, Degeler, Victoria, Groth, Paul   +2 more
openaire   +2 more sources

Imbalance‐Aware Credit Card Fraud Detection Using Multi‐Autoencoders and Generative Ensemble Learning

Expert Systems, Volume 43, Issue 5, May 2026.
ABSTRACT Credit card fraud detection remains a challenging research problem due to the class imbalance issue caused by the rarity of fraudulent transactions. Classical oversampling techniques such as SMOTE, ADASYN and their variants help balance data but do not reflect the nonlinear structure of real‐world fraud, leading to poor generalization.
Sultan Alharbi, Khalid Alahmadi, Xianzhi Wang   +2 more
wiley   +1 more source

An Analysis of Image Classification Using Wavelet-Based Autoencoder Architecture and Extreme Learning Machine

Journal of Electrical and Computer Engineering
In recent machine learning applications, promising outcomes have emerged through the integration of Deep Learning (DL) and Extreme Learning Machine (ELM) techniques with wavelet networks (WN), leading to high classification accuracy.
Salwa Said, Salima Hassairi, Siwar Yahia, Ridha Ejbali, Mourad Zaied   +4 more
doaj   +1 more source

Dual‐Branch Deep Neural Network for FLIM Parameter Estimation

Advanced Photonics Research, Volume 7, Issue 4, April 2026.
A dual‐branch deep network combining an autoencoder and a CNN is developed for fit‐free estimation in FLIM data. The proposed model was shown to outperform fit‐based method and single‐branch CNN model of the same complexity. Fluorescence lifetime imaging microscopy (FLIM) is a powerful tool for studying molecular interactions and cellular ...
Mou Adhikari, Kathrin Groeneveld, Matthias Klemm, Ralf Mrowka, Jens Haueisen, Shuxia Guo, Thomas Bocklitz   +6 more
wiley   +1 more source