Self-supervised Human Activity Recognition (HAR) has been gradually gaining a lot of attention in ubiquitous computing community. Its current focus primarily lies in how to overcome the challenge of ...

To make our anomaly detection lightweight, we further design a Light Convolutional Autoencoder (LightCAE) which contains a compressed autoencoder by exploiting tensor factorization to largely compress ...

In this paper, the stacked convolutional autoencoder network structure constructed with fusion selection kernel attention mechanism is based on FCAE, which consists of an encoder and a decoder.

The source code for the arXiv paper titled "KAE: Kolmogorov-Arnold Auto-Encoder for Representation Learning" is available. This code, created by Ruilizhen Hu, Fangchen Yu, and Yidong Lin, supports ...

Convolutional autoencoder, domain adaptation, and shallow classifiers. We first separately applies NMF on MIMIC and CHOA data for feature dimensionality reduction, then used two separate CAE models to ...

In this study, a deep convolutional neural network with deconvolution and a deep autoencoder (DDD) was proposed for the construction of an MSPC-based deep neural network that assesses the process ...

In this paper, through the experimental comparison of multi-layer perceptron, convolutional neural network, and the proposed convolutional autoencoder, we find that the constructed convolutional ...