Fruit category classification via an eight-layer convolutional neural network with parametric rectified linear unit and dropout technique

2018 ◽  
Vol 79 (21-22) ◽  
pp. 15117-15133 ◽  
Author(s):  
Shui-Hua Wang ◽  
Yi Chen
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Rectified Linear Unit ◽  
Parametric Rectified Linear Unit

Security of E-Health Systems Using Face Recognition Based on Convolutional Neural Network

2020 ◽  
Vol 2 (2) ◽  
pp. 37-41
Author(s):  
Zhixian Chen ◽  
Jialin Tang ◽  
Xueyuan Gong ◽  
Qinglang Su
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Convolutional Neural Network ◽  
Principal Component ◽  
Activation Function ◽  
Support Vector ◽  
Data Set ◽  
Novel Approach ◽  
Rectified Linear Unit ◽  
The Face

In order to improve the low accuracy of the face recognition methods in the case of e-health, this paper proposed a novel face recognition approach, which is based on convolutional neural network (CNN). In detail, through resolving the convolutional kernel, rectified linear unit (ReLU) activation function, dropout, and batch normalization, this novel approach reduces the number of parameters of the CNN model, improves the non-linearity of the CNN model, and alleviates overfitting of the CNN model. In these ways, the accuracy of face recognition is increased. In the experiments, the proposed approach is compared with principal component analysis (PCA) and support vector machine (SVM) on ORL, Cohn-Kanade, and extended Yale-B face recognition data set, and it proves that this approach is promising.

scholarly journals Reconfiguration layers of convolutional neural network for fundus patches classification

2021 ◽  
Vol 10 (1) ◽  
pp. 383-389
Author(s):  
Wahyudi Setiawan ◽  
Moh. Imam Utoyo ◽  
Riries Rulaningtyas
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Original Data ◽  
Max Pooling ◽  
Output Layer ◽  
Batch Normalization ◽  
Rectified Linear Unit ◽  
Input Layer ◽  
Fully Connected

Convolutional neural network (CNN) is a method of supervised deep learning. The architectures including AlexNet, VGG16, VGG19, ResNet 50, ResNet101, GoogleNet, Inception-V3, Inception ResNet-V2, and Squeezenet that have 25 to 825 layers. This study aims to simplify layers of CNN architectures and increased accuracy for fundus patches classification. Fundus patches classify two categories: normal and neovascularization. Data used for classification is MESSIDOR and Retina Image Bank that have 2,080 patches. Results show the best accuracy of 93.17% for original data and 99,33% for augmentation data using CNN 31 layers. It consists input layer, 7 convolutional layers, 7 batch normalization, 7 rectified linear unit, 6 max-pooling, fully connected layer, softmax, and output layer.

scholarly journals Deep Learning Based on Fourier Convolutional Neural Network Incorporating Random Kernels

Electronics ◽  
2021 ◽  
Vol 10 (16) ◽  
pp. 2004
Author(s):  
Yuna Han ◽  
Byung-Woo Hong
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Convolutional Neural Networks ◽  
Activation Function ◽  
Spatial Domain ◽  
Transformation Process ◽  
Real Component ◽  
Rectified Linear Unit ◽  
Classification Tasks

In recent years, convolutional neural networks have been studied in the Fourier domain for a limited environment, where competitive results can be expected for conventional image classification tasks in the spatial domain. We present a novel efficient Fourier convolutional neural network, where a new activation function is used, the additional shift Fourier transformation process is eliminated, and the number of learnable parameters is reduced. First, the Phase Rectified Linear Unit (PhaseReLU) is proposed, which is equivalent to the Rectified Linear Unit (ReLU) in the spatial domain. Second, in the proposed Fourier network, the shift Fourier transform is removed since the process is inessential for training. Lastly, we introduce two ways of reducing the number of weight parameters in the Fourier network. The basic method is to use a three-by-three sized kernel instead of five-by-five in our proposed Fourier convolutional neural network. We use the random kernel in our efficient Fourier convolutional neural network, whose standard deviation of the Gaussian distribution is used as a weight parameter. In other words, since only two scalars for each imaginary and real component per channel are required, a very small number of parameters is applied compressively. Therefore, as a result of experimenting in shallow networks, such as LeNet-3 and LeNet-5, our method achieves competitive accuracy with conventional convolutional neural networks while dramatically reducing the number of parameters. Furthermore, our proposed Fourier network, using a basic three-by-three kernel, mostly performs with higher accuracy than traditional convolutional neural networks in shallow and deep neural networks. Our experiments represent that presented kernel methods have the potential to be applied in all architecture based on convolutional neural networks.

scholarly journals Identifikasi Foto Wanita Berhijab dari Majalah Untuk Pembuatan Katalog Busana Muslim Otomatis Memanfaatkan Convolutional Neural Network

2019 ◽  
Vol 1 (2) ◽  
pp. 85-91
Author(s):  
M. Najamudin Ridha ◽  
Endang Setyati ◽  
Yosi Kristian
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Large Scale ◽  
Data Augmentation ◽  
Rectified Linear Unit

Abstrak—Perkembangan Fashion Muslim di Indonesia terus meningkat, disisi lain terobosan baru pada Deep Learning dengan memadukan arsitektur seperti dropout regularizations dan Rectified Linear Unit (ReLU) sebagai fungsi aktivasi dan data augmentation, mampu mencapai terobosan pada large scale image classification. Penelitian ini menggunakan metode deteksi objek wajah dengan Haar Cascades Classification untuk mendapatkan sample dataset wajah dan preprocessing data testing untuk dilanjutkan pada metode machine learning untuk klasifikasi citra dengan Convolutional Neural Network. Dataset yang digunakan adalah kumpulan katalog busana online, dataset yang sudah di preprocessing dibagi menjadi dua kategori, yaitu Hijab untuk semua citra wanita berhijab, dan Non Hijab untuk citra yang bukan wanita berhijab. selanjutnya klasifikasi citra menggunakan data ujicoba majalah digital terbitan Hijabella, Joy Indonesia dan Scarf Indonesia. Semakin besar resolusi citra input untuk preprocessing pada majalah digital, maka akan semakin banyak objek citra yang terdeteksi, dengan meningkatkan jumlah dataset untuk training dan validasi, mampu menambah hasil akurasi yang didapatkan, terjadi peningkatan akurasi pada dataset 2.500 wajah perkategori ke 5.000 wajah perkategori dengan resolusi 720p meningkat dari rata-rata 81.30% menjadi 82.31%, peningkatan rata-rata 1.01% dan tertinggi 2.14%, sedangkan resolusi 1080p meningkat dari rata-rata 83.03% menjadi 83.68%, peningkatan rata-rata 0.65% dan tertinggi 1.73%, akurasi tertinggi adalah sebesar 84.72% menggunakan model dataset 5.000 secara acak perkategori.

scholarly journals Enhanced Millimeter-Wave 3-D Imaging via Complex-Valued Fully Convolutional Neural Network

Electronics ◽  
2022 ◽  
Vol 11 (1) ◽  
pp. 147
Author(s):  
Handan Jing ◽  
Shiyong Li ◽  
Ke Miao ◽  
Shuoguang Wang ◽  
Xiaoxi Cui ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Millimeter Wave ◽  
Near Field ◽  
Back Propagation ◽  
Three Dimensional ◽  
Activation Function ◽  
Back Propagation Algorithm ◽  
Parametric Rectified Linear Unit ◽  
Complex Valued

To solve the problems of high computational complexity and unstable image quality inherent in the compressive sensing (CS) method, we propose a complex-valued fully convolutional neural network (CVFCNN)-based method for near-field enhanced millimeter-wave (MMW) three-dimensional (3-D) imaging. A generalized form of the complex parametric rectified linear unit (CPReLU) activation function with independent and learnable parameters is presented to improve the performance of CVFCNN. The CVFCNN structure is designed, and the formulas of the complex-valued back-propagation algorithm are derived in detail, in response to the lack of a machine learning library for a complex-valued neural network (CVNN). Compared with a real-valued fully convolutional neural network (RVFCNN), the proposed CVFCNN offers better performance while needing fewer parameters. In addition, it outperforms the CVFCNN that was used in radar imaging with different activation functions. Numerical simulations and experiments are provided to verify the efficacy of the proposed network, in comparison with state-of-the-art networks and the CS method for enhanced MMW imaging.

Sign in / Sign up

Export Citation Format

Share Document