scholarly journals Kinerja Algoritma Optimasi Root-Mean-Square Propagation dan Stochastic Gradient Descent pada Klasifikasi Pneumonia Covid-19 Menggunakan CNN

2021 ◽  
Vol 7 (3) ◽  
pp. 420
Author(s):  
Budi Nugroho ◽  
Eva Yulia Puspaningrum ◽  
M. Syahrul Munir
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Root Mean Square ◽  
Gradient Descent ◽  
Stochastic Gradient ◽  
Stochastic Gradient Descent ◽  
Mean Square ◽  
X Ray

Penelitian ini berkaitan dengan proses klasifikasi Pneumonia Covid-19 (radang paru-paru atau pneumonia yang disebabkan oleh virus corona SARS-CoV-2) dari citra hasil foto rontgen / x-ray paru-paru dengan menggunakan pendekatan pembelajaran mesin. Klasifikasi dilakukan untuk menentukan apakah kondisi paru-paru seseorang mengalami Pneumonia Covid-19, Pneumonia biasa, atau Normal / Sehat. Untuk menghasilkan kinerja klasifikasi yang lebih baik, proses optimasi seringkali digunakan pada tahap pelatihan data. Banyak teknik yang digunakan untuk melakukan optimasi tersebut, diantaranya adalah algoritma Root-Mean-Square Propagation (RMSprop) dan Stochastic Gradient Descent (SGD). Pada penelitian ini, pengujian dilakukan terhadap kedua metode tersebut untuk mengetahui kinerjanya pada klasifikasi Pneumonia Covid-19. Metode klasifikasi menggunakan Convolutional Neural Network (CNN) yang menerapkan 5 layer konvolusi dengan nilai filter 16, 32, 64, 128, dan 256. Proses pelatihan menggunakan 3.900 citra yang terdiri atas 1.300 citra pneumonia covid-19, 1.300 citra pneumonia, dan 1.300 citra normal. Sedangkan proses validasi menggunakan 450 citra dan proses pengujian mengunakan 225 citra. Berdasarkan uji coba yang telah dilakukan, implementasi algoritma optimasi RMSprop menghasilkan akurasi 87,99%, presisi 0,88, recall 0,86, dan f1 score 0,87. Sedangkan implementasi algoritma optimasi SGD menghasilkan akurasi 66,22%, presisi 0,69, recall 0,64, dan f1 score 0,67. Hasil ini memberikan informasi penting bahwa algoritma optimasi RMSprop menghasilkan kinerja yang jauh lebih baik daripada SGD pada klasifikasi Pneumonia Covid-19.

scholarly journals Multiclass Recognition of Offline Handwritten Devanagari Characters using CNN

2020 ◽  
Vol 5 (6) ◽  
pp. 1429-1439
Author(s):  
Mamta Bisht ◽  
Richa Gupta
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Character Recognition ◽  
Gradient Descent ◽  
Recognition Task ◽  
Stochastic Gradient ◽  
Stochastic Gradient Descent ◽  
Handwritten Character Recognition ◽  
Handwritten Documents ◽  
Acceptable Accuracy

The handwriting style of every writer consists of variations, skewness and slanting nature and therefore, it is a stimulating task to recognise these handwritten documents. This article presents a study on various methods available in literature for Devanagari handwritten character recognition and performs its implementation using Convolutional neural network (CNN). Available methods are studied on different parameters and a tabular comparison is also presented which concludes superiority of CNN model in character recognition task. The proposed CNN model results in well acceptable accuracy using dropout and stochastic gradient descent (SGD) optimizer.

scholarly journals Pengenalan Spesies Ikan Berdasarkan Kontur Otolith Menggunakan Convolutional Neural Network

2019 ◽  
Vol 2 (1) ◽  
pp. 41
Author(s):  
Heri Darmanto
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Discriminant Analysis ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Gradient Descent ◽  
Stochastic Gradient ◽  
Stochastic Gradient Descent ◽  
Processing Unit ◽  
Graphical Processing

Hasil sensus kehidupan laut pada tahun 2013 di seluruh dunia terdapat lebih dari 23.000 spesies dan masih banyak sekali spesies ikan yang belum diidentifikasi. Otolith merupakan organ yang sangat penting di belakang telinga ikan, karena melalui otolith ini dapat diketahui jenis ikan, pertumbuhan dan lingkungan, serta sejarah kehidupannya,  misalnya, umur, reproduksi, dan migrasi. Dengan semakin  canggihnya komputer dan pengolahan di bidang citra,  diharapkan  kemampuan  mengidentifikasi jenis  ikan  yang dimiliki oleh manusia bisa diadopsi  dan diterapkan pada perangkat komputer. Deep Learning saat ini semakin berkembang memanfaatkan sumber daya perangkat keras yang semakin canggih termasuk penggunaan GPU (Graphical Processing Unit) untuk perhitungan proses komputasi dengan akurasi yang lebih baik dan proses yang lebih cepat. Pada penelitian ini metode yang diusulkan, untuk keperluan klasifikasi ikan menggunakan metode Convolutional Neural Network dengan teknik Transfer Learning dari model Alexnet dan optimasi Momentum Stochastic Gradient Descent. Hasil eksperimen diperoleh akurasi sebesar 95.4% lebih tinggi dibanding metode Discriminant Analysis yang memiliki akurasi sebesar 92%.

scholarly journals Electrocardiogram Classification for Arrhythmia using Convolutional Neural Network 2D and Adabound Optimizer

2020 ◽  
Vol 8 (5) ◽  
pp. 1277-1284
Keyword(s):  
Neural Network ◽  
Cardiovascular Disease ◽  
Convolutional Neural Network ◽  
Gradient Descent ◽  
Stochastic Gradient Descent ◽  
Transform Method ◽  
The World ◽  
Optimal Accuracy ◽  
Deadly Disease ◽  
Electrocardiogram Ecg

Cardiovascular disease is the number one deadly disease in the world. Arrhythmia is one of the types of cardiovascular disease which is hard to detect but by using the routine electrocardiogram (ECG) recording. Due to the variety and the noise of ECG, it is very time consuming to detect it only by experts using bare eyes.Learning from the previous research in order to help the experts, this research develop 11 layers Convolutional Neural Network 2D (CNN 2D) using MITBIH Arrhythmia Dataset. The dataset is firstly preprocessed by using wavelet transform method, then being segmented by R-peak method. The challenge is how to conquer the imbalance and small amount of data but still get the optimal accuracy. This research can be helpful in helping the doctors figure out the type of arrhythmia of the patient. Therefore, this research did the comparison of various optimizers attach in CNN 2D namely, Adabound, Adadelta, Adagrad, Amsbound, Adam and Stochastic Gradient Descent (SGD). The result is Adabound get the highest performance with 91% accuracy and faster 1s training duration than Adam which is approximately 18s per epoch.

scholarly journals Improved Machine Learning Approach for Wavefront Sensing

Sensors ◽  
2019 ◽  
Vol 19 (16) ◽  
pp. 3533 ◽  
Author(s):  
Hongyang Guo ◽  
Yangjie Xu ◽  
Qing Li ◽  
Shengping Du ◽  
Dong He ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Root Mean Square Error ◽  
Convolutional Neural Network ◽  
Root Mean Square ◽  
Optical System ◽  
Wavefront Sensing ◽  
Mean Square ◽  
Point Spread Functions ◽  
Point Spread

In the adaptive optics (AO) system, to improve the effectiveness and accuracy of wavefront sensing-less technology, a phase-based sensing approach using machine learning is proposed. In contrast to the traditional gradient-based optimization methods, the model we designed is based on an improved convolutional neural network. Specifically, the deconvolution layer, which reconstructs unknown input by measuring output, is introduced to represent the phase maps of the point spread functions at the in focus and defocus planes. The improved convolutional neural network is utilized to establish the nonlinear mapping between the input point spread functions and the corresponding phase maps of the optical system. Once well trained, the model can directly output the aberration map of the optical system with good precision. Adequate simulations and experiments are introduced to demonstrate the accuracy and real-time performance of the proposed method. The simulations show that even when atmospheric conditions D/r0 = 20, the detection root-mean-square of wavefront error of the proposed method is 0.1307 λ, which has a better accuracy than existing neural networks. When D/r0 = 15 and 10, the root-mean-square error is respectively 0.0909 λ and 0.0718 λ. It has certain applicative value in the case of medium and weak turbulence. The root-mean-square error of experiment results with D/r0 = 20 is 0.1304 λ, proving the correctness of simulations. Moreover, this method only needs 12 ms to accomplish the calculation and it has broad prospects for real-time wavefront sensing.

MapReduce and Optimized Deep Network for Rainfall Prediction in Agriculture

2020 ◽  
Vol 63 (6) ◽  
pp. 900-912
Author(s):  
Oswalt Manoj S ◽  
Ananth J P
Keyword(s):  
Deep Learning ◽  
Gradient Descent ◽  
Prediction Models ◽  
Short Term Memory ◽  
Stochastic Gradient ◽  
Stochastic Gradient Descent ◽  
Mean Square ◽  
Rainfall Prediction ◽  
Gradient Descent Algorithm ◽  
Major Factors

Abstract Rainfall prediction is the active area of research as it enables the farmers to move with the effective decision-making regarding agriculture in both cultivation and irrigation. The existing prediction models are scary as the prediction of rainfall depended on three major factors including the humidity, rainfall and rainfall recorded in the previous years, which resulted in huge time consumption and leveraged huge computational efforts associated with the analysis. Thus, this paper introduces the rainfall prediction model based on the deep learning network, convolutional long short-term memory (convLSTM) system, which promises a prediction based on the spatial-temporal patterns. The weights of the convLSTM are tuned optimally using the proposed Salp-stochastic gradient descent algorithm (S-SGD), which is the integration of Salp swarm algorithm (SSA) in the stochastic gradient descent (SGD) algorithm in order to facilitate the global optimal tuning of the weights and to assure a better prediction accuracy. On the other hand, the proposed deep learning framework is built in the MapReduce framework that enables the effective handling of the big data. The analysis using the rainfall prediction database reveals that the proposed model acquired the minimal mean square error (MSE) and percentage root mean square difference (PRD) of 0.001 and 0.0021.

scholarly journals Neural ODEs as the deep limit of ResNets with constant weights

2020 ◽  
pp. 1-41 ◽  
Author(s):  
Benny Avelin ◽  
Kaj Nyström
Keyword(s):  
Neural Network ◽  
Gradient Descent ◽  
Deep Neural Network ◽  
Theoretical Foundation ◽  
Stochastic Gradient ◽  
Loss Functions ◽  
Stochastic Gradient Descent ◽  
Decay Estimates ◽  
Value Loss ◽  
Fokker Planck Equations

In this paper, we prove that, in the deep limit, the stochastic gradient descent on a ResNet type deep neural network, where each layer shares the same weight matrix, converges to the stochastic gradient descent for a Neural ODE and that the corresponding value/loss functions converge. Our result gives, in the context of minimization by stochastic gradient descent, a theoretical foundation for considering Neural ODEs as the deep limit of ResNets. Our proof is based on certain decay estimates for associated Fokker–Planck equations.

scholarly journals Deep Convolutional Spiking Neural Networks for Image Classification

2021 ◽  
Author(s):  
Ruthvik Vaila
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Gradient Descent ◽  
Stochastic Gradient ◽  
Spiking Neural Networks ◽  
Stochastic Gradient Descent ◽  
Data Set ◽  
Learning Capabilities ◽  
Artificial Neural

Spiking neural networks are biologically plausible counterparts of artificial neural networks. Artificial neural networks are usually trained with stochastic gradient descent (SGD) and spiking neural networks are trained with bioinspired spike timing dependent plasticity (STDP). Spiking networks could potentially help in reducing power usage owing to their binary activations. In this work, we use unsupervised STDP in the feature extraction layers of a neural network with instantaneous neurons to extract meaningful features. The extracted binary feature vectors are then classified using classification layers containing neurons with binary activations. Gradient descent (backpropagation) is used only on the output layer to perform training for classification. Surrogate gradients are proposed to perform backpropagation with binary gradients. The accuracies obtained for MNIST and the balanced EMNIST data set compare favorably with other approaches. The effect of the stochastic gradient descent (SGD) approximations on learning capabilities of our network are also explored. We also studied catastrophic forgetting and its effect on spiking neural networks (SNNs). For the experiments regarding catastrophic forgetting, in the classification sections of the network we use a modified synaptic intelligence that we refer to as cost per synapse metric as a regularizer to immunize the network against catastrophic forgetting in a Single-Incremental-Task scenario (SIT). In catastrophic forgetting experiments, we use MNIST and EMNIST handwritten digits datasets that were divided into five and ten incremental subtasks respectively. We also examine behavior of the spiking neural network and empirically study the effect of various hyperparameters on its learning capabilities using the software tool SPYKEFLOW that we developed. We employ MNIST, EMNIST and NMNIST data sets to produce our results.

Sign in / Sign up

Export Citation Format

Share Document