Supporting clustering with contrastive learning

D Zhang, F Nan, X Wei, S Li, H Zhu, K McKeown… - arxiv preprint arxiv …, 2021 - arxiv.org
Unsupervised clustering aims at discovering the semantic categories of data according to
some distance measured in the representation space. However, different categories often …

Som-vae: Interpretable discrete representation learning on time series

V Fortuin, M Hüser, F Locatello, H Strathmann… - arxiv preprint arxiv …, 2018 - arxiv.org
High-dimensional time series are common in many domains. Since human cognition is not
optimized to work well in high-dimensional spaces, these areas could benefit from …

Deep embedding clustering based on contractive autoencoder

B Diallo, J Hu, T Li, GA Khan, X Liang, Y Zhao - Neurocomputing, 2021 - Elsevier
Clustering large and high-dimensional document data has got a great interest. However,
current clustering algorithms lack efficient representation learning. Implementing deep …

ResNet autoencoders for unsupervised feature learning from high-dimensional data: Deep models resistant to performance degradation

CS Wickramasinghe, DL Marino, M Manic - IEEE Access, 2021 - ieeexplore.ieee.org
Efficient modeling of high-dimensional data requires extracting only relevant dimensions
through feature learning. Unsupervised feature learning has gained tremendous attention …

You never cluster alone

Y Shen, Z Shen, M Wang, J Qin… - Advances in Neural …, 2021 - proceedings.neurips.cc
Recent advances in self-supervised learning with instance-level contrastive objectives
facilitate unsupervised clustering. However, a standalone datum is not perceiving the …

Explainable unsupervised machine learning for cyber-physical systems

CS Wickramasinghe, K Amarasinghe, DL Marino… - IEEE …, 2021 - ieeexplore.ieee.org
Cyber-Physical Systems (CPSs) play a critical role in our modern infrastructure due to their
capability to connect computing resources with physical systems. As such, topics such as …

Deep discriminative clustering analysis

J Chang, Y Guo, L Wang, G Meng, S **ang… - arxiv preprint arxiv …, 2019 - arxiv.org
Traditional clustering methods often perform clustering with low-level indiscriminative
representations and ignore relationships between patterns, resulting in slight achievements …

Self‐supervised representation learning of metro interior noise based on variational autoencoder and deep embedding clustering

Y Wang, H **ao, Z Zhang, X Guo… - Computer‐Aided Civil …, 2025 - Wiley Online Library
The noise within train is a paradox; while harmful to passenger health, it is useful to
operators as it provides insights into the working status of vehicles and tracks. Recently …

Comparing stormwater quality and watershed typologies across the United States: A machine learning approach

CB Guzman, R Wang, O Muellerklein, M Smith… - Water Research, 2022 - Elsevier
Watersheds continue to be urbanized across different regions of the United States,
increasing the number of impaired waterbodies due to urban stormwater. Using machine …

GAN-based image-to-friction generation for tactile simulation of fabric material

S Cai, L Zhao, Y Ban, T Narumi, Y Liu, K Zhu - Computers & Graphics, 2022 - Elsevier
The electrovibration tactile display could render the tactile feeling of different textured
surfaces by generating the frictional force through voltage modulation. When a user is …