Comparative study of optimization techniques in deep learning: Application in the ophthalmology field

Aatila, Mustapha; Lachgar, Mohamed; Kartit, Ali

doi:10.1088/1742-6596/1743/1/012002

Cited by 29 publications

(11 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The need to use optimization training in the neural network helps for proper generalization of an algorithm and reduces the loss function by finding the optimized value of the weights. This enables accurate prediction of the new data [54].…”

Section: Phase 3: Optimization Techniquementioning

confidence: 99%

An Optimized Deep Learning Approach for Improving Airline Services

Ouf¹

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

The aviation industry is one of the most competitive markets. The most common approach for airline service providers is to improve passenger satisfaction. Passenger satisfaction in the aviation industry occurs when passengers' expectations are met during flights. Airline service quality is critical in attracting new passengers and retaining existing ones. It is crucial to identify passengers' pain points and enhance their satisfaction with the services offered. The airlines used a variety of techniques to improve service quality. They used data analysis approaches to analyze the passenger point data. These solutions have focused simply on surveys; consequently, deeplearning approaches have received insufficient attention. In this study, deep neural networks with the adaptive moment estimation Adam optimization algorithm were applied to enhance classification performance. In previous studies, the quality of the dataset has been ignored. The proposed approach was applied to the airline passenger satisfaction dataset from the Kaggle repository. It was validated by applying artificial neural networks (ANNs), random forests, and support vector machine techniques to the same dataset. It was compared with other research papers that used the same dataset and had a similar problem. The experimental results showed that the proposed approach outperformed previous studies. It has achieved an accuracy of 99.3%.

show abstract

Section: Phase 3: Optimization Techniquementioning

confidence: 99%

An Optimized Deep Learning Approach for Improving Airline Services

Ouf¹

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…Metode optimasi yang digunakan sangat menentukan tingkat konvergensi pemprosesan data. Beberapa optimasi yang bisa digunakan adalah AdaDelta, Nesterov, momentum, RMSProp, AdaGrad, Adam, Nadam GD algorithms dan AdaMax [12]. Metode estimasi Adam dan SGD sangat fleksibel dan memiliki tingkat konvergensi yang signifikan dan lebih cepat dibandingkan dengan metode lain, seperti yang dijelaskan Su dan Kek [13].…”

Section: Pendahuluanunclassified

Peramalan Data Cuaca Ekstrim Indonesia Menggunakan Model ARIMA dan Recurrent Neural Network

Hikmah

Asrirawan²,

Apriyanto³

et al. 2023

Jambura J. Math

View full text Add to dashboard Cite

Extreme weather modeling is a challenge for modeling experts in Indonesia and the world. Extreme weather prediction is a complex problem because the chances of it happening are very small, so the developed models often have a low level of accuracy. The purpose of this research is to combine the classic model, Autoregressive Integrated Moving Average (ARIMA), recurrent neural network (RNN) model using Adam and SGD estimation (RNN-Adam and RNN-SGD) with the reLU, tanh, sigmoid and gaussian activation functions. In addition, the ARIMA-RNN mix model was also demonstrated in this study. These models are applied to monthly period extreme weather data obtained from the Meteorology, Climatology and Geophysics Agency (BMKG) of West Sulawesi Province which are converted into training data and test data. The RMSE value is used to see the level of prediction accuracy in both training data and test data. Based on the research results, the best model obtained for modeling Indonesia’s extreme weather is the ARIMA-RNN-Adam mix model with the reLU activation function based on the RMSE value on the training and test data. At n = 50, the smallest RMSE and MSE values of the third model are the ARIMA-RNN-Adam model which is 0.23212 using the reLU activation function, then the ARIMA-RNN-SGD model which is 0.25432 with the same activation function, while the ARIMA value is 0.3270. At n=100 it can be seen that the smallest RMSE and MSE values of the three models are the ARIMA-RNN-Adam model which is equal to 0.25149 using the reLU activation function, then the ARIMA-RNN-SGD model which is equal to 0.25256 with the same activation function, while the ARIMA value is 0.2644.

show abstract

“…Adagrad offered to change the learning rate at each time step regarding the importance of parameters update [5]. However, Adagrad also has several disadvantages, it's computationally expensive as it needs to calculate second-order derivative, and as the learning rate decreases, it results in slow training, but the algorithm provides an approximate minimization, the speed of its convergence, this makes it possible to use it in future work using large data sets [20]. In (2) shows the weight update rule for Adagrad.…”

Section: Adaptive Gradient (Adagrad)mentioning

confidence: 99%

High performance of optimizers in deep learning for cloth patterns detection

Dewi

Salawangi

2023

IJ-AI

View full text Add to dashboard Cite

In Deep learning, optimization methods are an essential role. Optimizers are used to change weights and learn rates to reduce or minimize losses in a neural network. Nowadays, Deep Learning is widely used, especially in object detection tasks. In this case, cloth patterns are considered for object detection and assist visually impaired people. The visually impaired person had many limitations when doing their activity, not least when choosing clothes; it would be difficult without guidance or tools like Braille labels. In this research, a system was researched to detect 11 different cloth patterns (Argyle, Batik, Camouflage, Gingham, Dotted, Floral, Leopard, Solid, Striped, Zebra, and Zigzag) using RetinaNet with ResNet-152 architecture. To achieve the best model performance, compare 6 optimizers, such as Stochastic Gradient Descent, Root Mean Square Propagation, Adaptive Moment Estimation, Adaptive Delta, Adaptive Norm, and Adaptive Gradient was conducted. Each optimizer has trained with three different learning rates (1E-3, 1E-4, and 1E-5). A model with Adamax optimizer and learning rate 1E-4 was achieved with the highest accuracy with mAP (mean Average Precision) 91.28% during the training process. Based on the testing result this model was achieved precision 93.01%, recall 92.91%, F1-Score 92.79%, and accuracy 92.91%.

show abstract

Comparative study of optimization techniques in deep learning: Application in the ophthalmology field

Cited by 29 publications

References 7 publications

An Optimized Deep Learning Approach for Improving Airline Services

An Optimized Deep Learning Approach for Improving Airline Services

Peramalan Data Cuaca Ekstrim Indonesia Menggunakan Model ARIMA dan Recurrent Neural Network

High performance of optimizers in deep learning for cloth patterns detection

Contact Info

Product

Resources

About