Suchergebnisse - Sparse denoised autoencoder

Convolutional autoencoder-augmented sparse identification of noisy nonlinear fluid dynamics from unlabelled data

Autoren: Meng Zhang Fanfan Zeng Mustafa Z. Yousif et al.

Quelle: Physics of Fluids. 37

A denoising method for ECG signals based on CEEMDAN-TSO and stacked sparse autoencoders

Autoren: Shun Li Juan Li Jiandong Mao et al.

Quelle: Computers in Biology and Medicine. 188:109818

Zugangs-URL: https://pubmed.ncbi.nlm.nih.gov/39983358

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering

Autoren: Zhao, Haiyan Wu, Xuansheng Yang, Fan et al.

Schlagwörter: FOS: Computer and information sciences, Artificial Intelligence (cs.AI), Artificial Intelligence, Computation and Language, Computation and Language (cs.CL)

Zugangs-URL: http://arxiv.org/abs/2505.15038

Denoised Internal Models: A Brain-inspired Autoencoder Against Adversarial Attacks

Autoren: Kai-Yuan Liu Xing-Yu Li Yu-Rui Lai et al.

Quelle: Machine Intelligence Research. 19:456-471

Schlagwörter: FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology, 01 natural sciences, 0105 earth and related environmental sciences

Zugangs-URL: http://arxiv.org/abs/2111.10844

Denoised Internal Models: a Brain-Inspired Autoencoder against Adversarial Attacks

Autoren: Liu, Kaiyuan Li, Xingyu Lai, Yurui et al.

Index Begriffe: Computer Science - Computer Vision and Pattern Recognition, text

URL: http://arxiv.org/abs/2111.10844

Adaptive mobilenetv3 with spatial attention-aided effective brain tumor classification approach using denoised image-based segmentation

Autoren: Kulkarni Sheetal Vijay S. Poornapushpakala

Quelle: International Journal of Innovative Research and Scientific Studies. 8:157-179

Denoising Autoencoder for Reconstructing Sensor Observation Data and Predicting Evapotranspiration: Noisy and Missing Values Repair and Uncertainty Quantification.

Autoren: Johnsen, Timothy K. Bi, Xiangyu Chou, Chunwei et al.

Quelle: Water Resources Research; Oct2025, Vol. 61 Issue 10, p1-23, 23p

Schlagwörter: EVAPOTRANSPIRATION, AUTOENCODERS, STOCHASTIC analysis, MACHINE learning, HYDROLOGICAL forecasting, NOISE control, TELEMETRY

Fault detection and recognition of multivariate process based on feature learning of one-dimensional convolutional neural network and stacked denoised autoencoder.

Autoren: Zhang, Chengyi Yu, Jianbo Wang, Shijin

Quelle: International Journal of Production Research; Apr2021, Vol. 59 Issue 8, p2426-2449, 24p, 2 Color Photographs, 3 Diagrams, 15 Charts, 4 Graphs

Schlagwörter: CONVOLUTIONAL neural networks, SIGNAL convolution, FAULT diagnosis, ARTIFICIAL neural networks, MANUFACTURING processes, SIGNAL processing, DEEP learning, CONVEYOR belts

Efficient protein structure generation with sparse denoising models.

Autoren: Jendrusch, Michael Korbel, Jan O.

Quelle: Nature Machine Intelligence; Sep2025, Vol. 7 Issue 9, p1429-1445, 17p

Enhanced heart sound anomaly detection via WCOS: a semi-supervised framework integrating wavelet, autoencoder and SVM.

Autoren: Zeng, Peipei Kang, Shuimiao Fan, Fan et al.

Quelle: Frontiers in Neuroinformatics; 2025, p1-15, 15p

Schlagwörter: ANOMALY detection (Computer security), HEART murmurs, SUPPORT vector machines, CONGENITAL heart disease, AUTOENCODERS

An Approach for EEG Denoising Based on Wasserstein Generative Adversarial Network.

Autoren: Dong, Yuanzhe Tang, Xi Li, Qingge et al.

Quelle: IEEE Transactions on Neural Systems & Rehabilitation Engineering; 2024, Vol. 31, p3524-3534, 11p

Schlagwörter: GENERATIVE adversarial networks, HILBERT-Huang transform, BRAIN-computer interfaces, AUTOENCODERS, FEATURE extraction, ELECTROENCEPHALOGRAPHY

Deep Residual Autoencoders for Expectation Maximization-Inspired Dictionary Learning.

Autoren: Tolooshams, Bahareh Dey, Sourav Ba, Demba

Quelle: IEEE Transactions on Neural Networks & Learning Systems; Jun2021, Vol. 32 Issue 6, p2415-2429, 15p

Schlagwörter: IMAGE denoising, RECURRENT neural networks, EXPECTATION-maximization algorithms, REGULARIZATION parameter

A Novel Deep Neural Network-Based Framework for Subsurface Analysis in Non-Stationary Thermal Wave Imaging.

Autoren: Swapna, M. N. Suman, M. Prasanthi, Y. N. et al.

Quelle: Sensing & Imaging; 9/5/2025, Vol. 26 Issue 1, p1-18, 18p

Deep spectral unmixing framework via 3D denoising convolutional autoencoder.

Autoren: Jia, Peiyuan Zhang, Miao Shen, Yi

Quelle: IET Image Processing (Wiley-Blackwell); May2021, Vol. 15 Issue 7, p1399-1409, 11p

Schlagwörter: HYPERSPECTRAL imaging systems, IMAGE denoising, IMAGE processing, PIXELS, GEOMETRIC analysis, DATA

Sparsity‐based autoencoders for denoising cluttered radar signatures

Autoren: Shobha Sundar Ram Shelly Vishwakarma Akanksha Sneh et al.

Quelle: IET Radar, Sonar & Navigation, Vol 15, Iss 8, Pp 915-931 (2021)

Schlagwörter: DECOMPOSITION, Signal Processing (eess.SP), Technology, Science & Technology, RECOGNITION, INDOOR, HUMANS, TK5101-6720, 02 engineering and technology, TRACKING, Engineering, Telecommunications, Telecommunication, FOS: Electrical engineering, electronic engineering, information engineering, 0202 electrical engineering, electronic engineering, information engineering, Electrical & Electronic, MICRO-DOPPLER, Electrical Engineering and Systems Science - Signal Processing

Zugangs-URL: https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/rsn2.12065
http://arxiv.org/abs/2101.12445
https://doaj.org/article/bb17211ced3c4eebbff492b80e86e468
https://ietresearch.onlinelibrary.wiley.com/doi/full/10.1049/rsn2.12065
https://discovery-pp.ucl.ac.uk/id/eprint/10129609/

Denoising Autoencoder Aided Spectrum Reconstruction for Colloidal Quantum Dot Spectrometers

Autoren: Jinhui Zhang Xueyu Zhu Jie Bao

Quelle: IEEE Sensors Journal. 21:6450-6458

Schlagwörter: 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology, 01 natural sciences

Zugangs-URL: https://ui.adsabs.harvard.edu/abs/2021ISenJ..21.6450Z/abstract
https://ieeexplore.ieee.org/document/9269398/

Speaker Identification by Atomic Decomposition of Learned Features Using Computational Auditory Scene Analysis Principals in Noisy Environments

Autoren: Thomas Bryan Veton Kepuska Ivica Kostanic

Schlagwörter: Time-frequency plane, atomic decomposition, envelope sampling, Gabor atoms, matching pursuit, sparse dictionary learning, sparse autoencoder

Relation: https://zenodo.org/communities/waset/; https://zenodo.org/records/1124331; oai:zenodo.org:1124331; https://doi.org/10.5281/zenodo.1124331

Verfügbarkeit: https://doi.org/10.5281/zenodo.1124331
https://zenodo.org/records/1124331

Extract Features Using Stacked Denoised Autoencoder.

Autoren: Gao, Yushu Zhu, Lin Zhu, Hao-Dong et al.

Quelle: Intelligent Computing in Bioinformatics; 2014, p10-14, 5p

Convolutional autoencoder-augmented sparse identification of noisy nonlinear fluid dynamics from unlabelled data.

Autoren: Zhang, Meng Zeng, Fanfan Yousif, Mustafa Z. et al.

Quelle: Physics of Fluids; Sep2025, Vol. 37 Issue 9, p1-15, 15p

Schlagwörter: FLUID dynamics, AUTOENCODERS, NONLINEAR mechanics, FLOW simulations, TURBULENT flow, METADATA, SPARSE approximations, NOISE control

Adaptive mobilenetv3 with spatial attention-aided effective brain tumor classification approach using denoised image-based segmentation.

Autoren: Vijay, Kulkarni Sheetal Poornapushpakala, S.

Quelle: International Journal of Innovative Research & Scientific Studies; 2025, Vol. 8 Issue 6, p157-179, 23p

Schlagwörter: BRAIN tumors, CLASSIFICATION, IMAGE denoising, IMAGE segmentation, ATTENTION, CONVOLUTIONAL neural networks, MAGNETIC resonance imaging