Comparison of Multilayer Perceptron’s Activation and Op-Timization Functions in Classification of Covid-19 Patients

Rice is an intriguing research topic, particularly in computer vision fields, because it is a staple food consumed in many parts of the world. Different rice varieties can be classified using the rice grain image based on their textures, sizes, and colors. To extract features from rice images, we used two popular pre trained convolutional neural network models, Inception V3 and VGG 16. The extracted features are then used as transfer learning in six variations of multilayer perceptron models, using rectified linear units as the activation function and adaptive moments as the loss function. The results show that the VGG 16 network performs better than the Inception V3, with 0.5% higher accuracy, precision, and recall value. Also, using the VGG 16 network produces a lower misclassification percentage, compared to the Inception V3 network, with a difference of 2.6%.

Section: E Evaluationmentioning

confidence: 99%

Inception-V3 Versus VGG-16: in Rice Classification Using Multilayer Perceptron

Firmansyah¹,

Rosnelly

Wanayumini³

2023

“…The results of this grouping are used as targets in the classification process using the six models of the RF algorithm, consisting of a different number of trees, with Table III showing the model's configuration. After obtaining the classification results using the above models, we evaluate each model's performance according to the accuracy, precision, and recall values using equations ( 2) to (4) [28].…”

Section: Sentiment Classificationmentioning

confidence: 99%

Comparison Of SGD, Rmsprop, and Adam Optimation In Animal Classification Using CNNs

Irfan¹,

Gunawan²,

Wanayumini³

2023

Many measures have been taken to protect endangered species by using "camera trap" technology which is widespread in the field of technology-based nature protection field research. In this study, a machine learning-based approach is presented to identify endangered wildlife images with a data set containing 5000 images taken from Kaggle and some other sources. The Gradient Descent optimization method is often used for Artificial Neural Network (ANN) training. This method plays a role in finding the weight values that give the best output value. Three optimization methods have been implemented, namely Stochastic Gradient Descent (SGD), ADADELTA, and Adam on the Artificial Neural Network system for animal data classification. In some of the studies reviewed there are differences in the results of SGD and ADAM, which on the one hand SGD is superior, and on the one hand ADAM is superior with the appropriate learning rate. The results of this study show that the CNN method with the Adam optimization function produces the highest accuracy compared to the SGD and RMSprop optimization methods. The model trained using Adam's optimization function achieved an accuracy of 89.81% on the test, showing the feasibility of the approach.

“…To evaluate the classification results produced by the two models designed, we use the 10-fold cross-validation to generate the actual and predicted result in a confusion matrix table. Based on the comparison values in the confusion matrix output, we calculate the accuracy, precision, and recall values using equations ( 4) to ( 6) and use them as a reference to evaluate the classification results of each model [28]. The model that produces the highest values is the model concluded as the model with the best classification performance.. R ESULTS A ND D ISCUSSIONS From the data collection using the Twitter API and the "#blokirkominfo" keyword, we got 1000 tweets that fulfilled the keywords.…”

Section: G Evaluationmentioning

confidence: 99%

Sentiment Analysis of IDAHOBIT Celebrations using Naïve Bayes and Decision Tree Algorithms

Kusuma¹,

Hartono

Hayadi

2023

The development of LGBTIQ in Indonesia reflects the shift in culture and the emergence of this phenomenon has attracted the attention of the Indonesian people. The use of NLP, ML, and statistics technology in tweet analysis can be used to identify sentiments contained in tweets. This study compares Naïve Bayes algorithm and Decision Tree in sentiment analysis classification, in which the multilingual sentiment analysis method is used in the labeling process of training data. Naïve Bayes results give the best classification with 100% accuracy, precision, and recall, and the number of positive sentiments is 385, negative sentiments are 3117, and neutral sentiments are 899. It looks that the negative class is the most superior compared to other classes. This proves that the Indonesian people have an unfavorable response to the IDAHOBIT celebration.