In this paper, we develop a hybrid deep learning-based fruit image classification framework, named attention-based densely connected convolutional networks with convolution autoencoder (CAE-ADN), which uses a convolution autoencoder to pre-train the images and uses an attention-based DenseNet to ...
For instance, Bedi and Gole [11] proposed a novel hybrid model based on a convolutional autoencoder (CAE) network and convolutional neural network (CNN) for automatic plant disease detection. Reference [12] used a convolutional neural network to extract features from a large dataset containing ...
Duan R, Chen Z, Zhang H et al (2023) Dual residual denoising autoencoder with channel attention mechanism for modulation of signals. Sensors 23(2):1023. https://doi.org/10.3390/s23021023 Article Google Scholar Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. ...
one-dimensional convolutional autoencoderssurrogate modelThis paper proposes a one‐dimensional convolutional autoencoders (1D‐CAE) surrogate‐based electromagnetic (EM) optimization technique exploiting particle swarm optimization (PSO) algorithm for microwave filter design. The 1D‐CAE is a flexible ...
In this paper, a Convolution Autoencoder (CAE) is used to obtain high-level feature representations from the input signature and these high level features are fused with handcrafted features to constitute a hybrid feature set. The hybrid set of features is presented as an input to an Online ...
This paper aims to explore how to combine convolutional autoencoder (CAE) and genetic algorithm (GA) to construct an efficient network attack detection model and improve the ability of network security defense. First, the convolutional autoencoder is used to effectively learn the feature ...
convolution auto-encodersPCAINFRARED-SPECTROSCOPYSELECTIONAiming at classification and recognition of aero-engines, two telemetry Fourier transform infrared (FT-IR) spectrometers are utilized to measure the infrared spectrum of the areo-engine hot jet, meanwhile a spectrum dataset of six types of areo-...
(a) The reconstruction results of the baseline convolution auto-encoder (CAE), the CAE with the compact depth-wise separable convolution (CSeConv) layer (CCAE), the CAE with the compact separable deconvolution (CSeDeConv) layer (CDCAE), and the compact CAE with the CSeConv layer and CSe...
This work presents a multilayer perceptron-convolutional auto-encoder (MLP-CAE) neural network, which accurately predicts the two-dimensional flame dynamics of an acoustically excited premixed laminar flame. The architecture maps the acoustic perturbation time series into a heat release rate field, ...
In the first detection step, the onedimensional convolutional autoencoder (1D-CAE) is employed to obtain the reconstruction error as anomaly scores from the raw EMI data. Hence, the faulty PZT sensors can be detected by comparing the anomaly score with a pre-defined threshold. In the second ...