Results 111 to 120 of about 247,960 (211)

DSFC-AE: A New Hyperspectral Unmixing Method Based on Deep Shared Fully Connected Autoencoder

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
The pervasive presence of mixed pixels in hyperspectral remote sensing imagery poses a substantial constraint on the quantitative progress of remote sensing technology. Hyperspectral unmixing (HU) techniques serve as effective means to address this issue.
Hao Chen 0192, Tao Chen 0004, Yuxiang Zhang 0001, Bo Du 0001, Antonio Plaza   +4 more
openaire   +2 more sources

Transfer Learning for Generalising a Hybrid Autoencoder-Isolation Forest Model for Time Series Anomaly Detection in ARRONAX Cyclotron Operational Data

International audiencePrior work problem [3]: Isolation Forest (IF) struggles to detect local anomalies near the normal mean due to axis-parallel splits.
Haddad, Ferid, Mateus, Diana, Poirier, Freddy, Basbous, Fatima   +3 more
core   +3 more sources

Method for Detecting Disorder of a Nonlinear Dynamic Plant

Sensors
This paper proposes a new disorder detection method CCF-AE for a scalar dynamic plant based only on its input–output relation using a cross-correlation function and neural network autoencoder.
Xuechun Wang, Vladimir Eliseev
doaj   +1 more source

End-to-end optimization based on residual neural networks for improved optical fiber communication

ICT Express
High-capacity optical fiber transmissions increasingly face performance limits imposed by nonlinear transmission effects. This paper examines deep learning-based enhancements in optical fiber communication through an end-to-end autoencoder (AE) framework.
Omar Alnaseri, Mohammed Alaa Ala’anzy, Nasir Saeed   +2 more
doaj   +1 more source

CFS-AE: Correlation-based Feature Selection and Autoencoder for Improved Intrusion Detection System Performance

Journal of Internet Services and Information Security
The major problem computer network users face concerning data – whether in storage, in transit, or being processed - is unauthorized access. This unauthorized access typically leads to the loss of confidentiality, integrity, and availability of data.
Seiba Alhassan, Gaddafi Abdul-Salaam, Asante Micheal, Yaw Marfo Missah, Ernest Domanaanmwi Ganaa, Alimatu Sadia Shirazu   +5 more
openaire   +2 more sources

Autoencoder-assisted Feature Ensemble Net for Incipient Faults [PDF]

Deep learning has shown the great power in the field of fault detection. However, for incipient faults with tiny amplitude, the detection performance of the current deep learning networks (DLNs) is not satisfactory.
Gao, Mingxuan, Chen, Maoyin, Wang, Min
core  

Research on a lead-acid battery fault detection method based on LSTM-AE-Cosine. [PDF]

PLoS One
Liu L, Xu H, Tang H, Cui J, Feng L, Deng K.   +5 more
europepmc   +1 more source

Speech-based early depressive symptom screening using MAX-Net: a multi-scale autoencoder-augmented xLSTM framework. [PDF]

Front Psychiatry
Zheng Z, Liang L, Zhang J, Wang G, Xue C.   +4 more
europepmc   +1 more source

ROI-SSIM guided framework for 3D knee MRI reconstruction under artifact degradation. [PDF]

MethodsX
Bekbolat A, Askhatova A, Niyetkaliyev A, Jamwal P, Ozhikenov K, Alimbayeva Z, Beisembekova R, Igembay Y.   +7 more
europepmc   +1 more source

AE-DTNN: Autoencoder–Dense–Transformer Neural Network Model for Efficient Anomaly-Based Intrusion Detection Systems

In this study, we introduce an enhanced hybrid Autoencoder–Dense–Transformer Neural Network (AE-DTNN) model for developing an effective intrusion detection system (IDS) aimed at improving the performance and robustness of threat detection ...
Maggie Mashaly, Hesham Kamal
core   +1 more source