Article Per Year (5 Year)
p-Index From 2020 - 2025
1.323
P-Index
This Author published in this journals
All Journal Proceeding of International Conference on Information Science and Technology Innovation (ICoSTEC)
Rika Rosnelly
Magister of Computer Science, Potensi Utama University
Computer Science & IT

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 9 Documents
Search

 1 
Inception-V3 Versus VGG-16: in Rice Classification Using Multilayer Perceptron Ichsan Firmansyah; Rika Rosnelly; Wanayumini Wanayumini
Proceeding of International Conference on Information Science and Technology Innovation (ICoSTEC) Vol. 2 No. 1 (2023): Proceeding of International Conference on Information Science and Technology In
Publisher : Universitas Respati Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/icostec.v2i1.24

Abstract

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%.
Classification of Shape Bean Coffee Using Convolutional Neural Network P.P.P.A.N.W. Fikrul Ilmi R.H. Zer; Rika Rosnelly; Wanayumini Wanayumini
Proceeding of International Conference on Information Science and Technology Innovation (ICoSTEC) Vol. 2 No. 1 (2023): Proceeding of International Conference on Information Science and Technology In
Publisher : Universitas Respati Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/icostec.v2i1.25

Abstract

Deep Learning is a sub-field of Machine Learning in addressing the development of an image classification. This study uses a Deep Learning algorithm to classify the shape of coffee beans which consist of 4 types, namely defect, longberry, peaberry and premium. We use the Convolutional Neural Network to classify the shape of the coffee beans. This study combines the Convolutional Neural Network algorithm with Adam's optimization to get the best results. The research dataset uses training data of 4800 images and testing data of 1600 images with four classes. The results of this study get an accuracy result of 90,63%, a precision result of 88,23%, and a recall result of 95,74%. Based on the results obtained that the Convolutional Neural Network with Adam's optimization can be applied to the classification of coffee bean shapes with good results.
Transfer Learning for Feral Cat Classification Using Logistic Regression Fazli Nugraha Tambunan; Rika Rosnelly; Zakarias Situmorang
Proceeding of International Conference on Information Science and Technology Innovation (ICoSTEC) Vol. 2 No. 1 (2023): Proceeding of International Conference on Information Science and Technology In
Publisher : Universitas Respati Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/icostec.v2i1.27

Abstract

Machine learning is an alternative tool for classifying animal species, especially feral cats. In this research, we use a machine learning algorithm to classify three species of feral cats: American Wildcat, Black-footed Cat, and European Wildcat. We also use a transfer learning model using the VGG-19 network for extracting the features in the feral cat images. By combining the VGG-19 and logistic regression algorithm, we build six models and compare which one is the best to solve the problem. We evaluate and analyze all models using a 5-fold, 10-fold, and 20-fold cross-validation, with accuracy, precision, and recall as the base performance value. The best result obtained is a model with a lasso regularization and cost parameter value of 1, with an accuracy value of 0.846667, a precision value of 0.845389, and a recall value of 0.846667. We also tune the C parameter in each LR model with values such as 0.1, 0.5, and 1. The most optimum C value for the lasso and ridge regularization is one, resulting in an average value of accuracy = 0.813, precision = 0.812, and recall = 0.813.
Combination of Pre-Trained CNN Model and Machine Learning Algorithm on Pekalongan Batik Motif Classification Masri Wahyuni; Rika Rosnelly; Wanayumini Wanayumini
Proceeding of International Conference on Information Science and Technology Innovation (ICoSTEC) Vol. 2 No. 1 (2023): Proceeding of International Conference on Information Science and Technology In
Publisher : Universitas Respati Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/icostec.v2i1.28

Abstract

Pekalongan is a region in Indonesia well-known for its batik production. The Pekalongan batik is rich in varieties of motifs, such as the Jlamprang, Liong, Terang Bulan, and Tujuh Rupa. The difficulty of distinguishing Pekalongan batik motifs for ordinary people causes the need for a model that can help recognize these motifs automatically based on input from digital images. This research aims to classify the Pekalongan batik motifs using a pre-trained Convolutional Neural Network (CNN), the Inception V3, and machine learning, the K-Nearest Neighbors (K-NN) algorithm. First, we extract the features from the digital image using the Inception V3 model, resulting in m x 2048 features, where m is the number of images. The extracted features generated from the Inception V3 model will be used as the dataset for the motif classification. We build models to classify the features using the K-Nearest Neighbors (KNN) with a K value of 5. In the classification process, we employ two distance metrics, the Euclidean and Manhattan distance, and analyze their performance using the 10-fold and 20-fold crossvalidation. The results of this study are the highest overall performace of accuracy (0.987), precision (0.987), and recall (0.987) produced by the Euclidean model.
Bulldog Breed Classification Using VGG-19 and Ensemble Learning Abwabul Jinan; Zakarias Situmorang; Rika Rosnelly
Proceeding of International Conference on Information Science and Technology Innovation (ICoSTEC) Vol. 2 No. 1 (2023): Proceeding of International Conference on Information Science and Technology In
Publisher : Universitas Respati Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/icostec.v2i1.29

Abstract

In image classification, the C4.5, Adaboost, and Gradient Boosting algorithms need another method to extract the image's features in the classification process. This research employs transfer learning with the VGG-19 network for the image's features extraction and transfers the result as a dataset to classify image-based Bulldog breeds. As the classifier to classify the extracted features from the VGG 16 model, we employ three ensemble learning algorithms, namely C4.5, AdaBoost, and Gradient Boost. The training data classification results of the American, English, and French bulldog breeds show that, with a 20-fold cross-validation evaluation, the Gradient Boosting algorithm performs the best, with an accuracy value of 0.958, a precision value of 0.958 and recall value of 0.933. And show the highest accuracy (0.933), precision (0.938), and recall (0.933) in the testing data classification. While in the testing data classification, the Gradient Boosting algorithm scores an accuracy value of 0.933, a precision value of 0.938, and a recall value of 0.933
A Combination Of Support Vector Machine And Inception-V3 In Face-Based Gender Classification Doughlas Pardede; Wanayumini Wanayumini; Rika Rosnelly
Proceeding of International Conference on Information Science and Technology Innovation (ICoSTEC) Vol. 2 No. 1 (2023): Proceeding of International Conference on Information Science and Technology In
Publisher : Universitas Respati Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/icostec.v2i1.30

Abstract

Differences in human facial structures, especiallythose recorded in a digital image, can be used as an automaticgender comparison tool. This research utilizes machine learning using the support vector machine (SVM) algorithm to perform gender identification based on human facial images. The transfer learning technique using the Inception-v3 model is combined with the SVM algorithm to produce six models that implement polynomial, radial basis function (RBF), and sigmoid kernel functions. The results obtained are models with excellent performance, as seen from the lowest values of accuracy = 0.852, precision = 0.856, recall = 0.852, and the highest values of 0.957, 0.957, and 0.957. This combination also produces a model with excellent reliability, where the probability of overfitting or underfitting obtained is below 1%.
Classification of Basurek Batik Using Pre-Trained VGG16 and Support Vector Machine Meli Handayani; Rika Rosnelly; Hartono Hartono
Proceeding of International Conference on Information Science and Technology Innovation (ICoSTEC) Vol. 2 No. 1 (2023): Proceeding of International Conference on Information Science and Technology In
Publisher : Universitas Respati Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/icostec.v2i1.31

Abstract

By introducing Indonesian batik motifs, we know that the island of Sumatra, especially Bengkulu and Jambi provinces, has a distinctive batik called Basurek batik. This research aims to classify the two batik motifs using the Support Vector Machine (SVM) algorithm. First, we extract the image of the batik motif with a pre-trained VGG-16 model and then use them as a dataset for the SVM classification process. The classification process itself uses linear, polynomial, and sigmoid kernels. We divided the data 90:10 and used 10-fold cross-validation to analyze each training and testing data classification result. The results of this study are the highest values of accuracy, precision, and recall of 76.4%, 76.5%, and 76.4% produced by the linear kernel for the training data classification. For the testing data classification, both the linear and polynomial kernels generate the best accuracy, precision, and recall values of 87.5%, 90%, and 85.5%. On average, incorporating the training and testing classification results, we found that the linear kernel is the best function for classifying the Basurek batik motif using the collected images from the internet.
HYPERTEROID DISEASE ANALYSIS WITH BACKPROPAGATION ARTIFICIAL NEURAL NETWORK Ela Roza Batubara; Muhammad Zarlis; Rika Rosnelly
Proceeding of International Conference on Information Science and Technology Innovation (ICoSTEC) Vol. 2 No. 1 (2023): Proceeding of International Conference on Information Science and Technology In
Publisher : Universitas Respati Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/icostec.v2i1.34

Abstract

In the era of technology 4.0, a system is needed to support the development of a company, both in industry, education, and others to help solve problems. In this study, the authors used the Backpropagation Neural Network Algorithm in recognizing hyperthyroid disease patterns. In this study, in the recognition of hyperthyroid disease patterns. The author uses 11 data variables that will be trained using the backpropagation algorithm where the weighting is done randomly and the second data is trained using the backpropagation algorithm. In this study using Matlab application for processing. From the results of testing data derived from kaggle, namely hyperthyroid disease data above, we can see in the 2-2-1 architecture which shows that the target is reduced by the jst output that the SSE is 0.06571 which indicates that there is an increase in hyperthyroid disease activity in humans. From the data obtained, that the performance of artificial neural network calculations with the Backpropagation Algorithm is 86%. Can be seen by comparing the desired target with the prediction target.
Comparative Analysis of Support Vector Machine And Perceptron Algorithms In Classification Of The Best Work Programs In P2KBP3A Jaka Tirta Samudra; Rika Rosnelly; Zakarias Situmorang
Proceeding of International Conference on Information Science and Technology Innovation (ICoSTEC) Vol. 2 No. 1 (2023): Proceeding of International Conference on Information Science and Technology In
Publisher : Universitas Respati Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/icostec.v2i1.40

Abstract

With the rapid growth of government agencies that are required to carry out an activity in every aspect that publishes and carries out obligations every year, it is required to be held accountable and also implemented for every device that receives such as fostered villages by utilizing the available APBD funds to maximize the work program that has been designed. so that it can be implemented as much as possible. That way, to get the best from all aspects of every work program implementation, there must be an important point from the annual work program design that is made without exception. Data mining itself can help P2KBP3A in analyzing each work program that is designed before being implemented in the future for the annual work program by looking at various aspects of past work program data and grouping work programs in the form of classification. In designing the work program, this research builds a classification model by adding a sigmoid activation function that uses SVM and perceptron to compare the accuracy results of the algorithm used to get the best work program design. From the various classifications used, the best value for classifying the dataset of the best P2KBP3A work programs can be seen from the average accuracy value of 87.5%, F1 value of 82.2%, the precision value of 80.2%, and recall value of 87.5%
Co-Authors Doughlas Pardede Ela Roza Batubara Fazli Nugraha Tambunan Hartono Hartono Ichsan Firmansyah Jaka Tirta Samudra Jinan, Abwabul Masri Wahyuni Meli Handayani Muhammad Zarlis P.P.P.A.N.W. Fikrul Ilmi R.H. Zer Wanayumini Zakarias Situmorang