Garuda - Garba Rujukan Digital

Pengenalan Golongan Jenis Kendaraan Bermotor pada Ruas Jalan Tol Menggunakan CNN Ricky Herwanto; Kartika Gunadi; Endang Setyati
Jurnal Infra Vol 8, No 1 (2020)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Payment system at the toll gate has been improved, from using physical money replace with e-money. The system needs to which class types of the vehicle entering the toll gate so the system can know how much will it take from the e-money. There are five class types of vehicles, but there are still many toll gates that have high limit to limit the class of vehicles that can enter, making it difficult for class types other than the first class type because they only have a few gates. This research uses You Only Look Once and Convolutional Neural Network as its methods. You Only Look Once is used to detect the location of the vehicle in the image. Convolutional Neural Network is used to classify the class types of the vehicle in the image. For convolutional neural network model, one well-known model is VGG16 which is good in classifying images. The result of this research that will be displayed is the classified of the class type of the vehicle in the form of strings. The result from tests that were done is an accuracy of 93.5% and f-score of 81.37% from self-configuration convolutional neural network and an accuracy of 90.76% and f-score of 73.53% for VGG16 model.

Deteksi Helm pada Pengguna Sepeda Motor dengan Metode Convolutional Neural Network Albert Albert; Kartika Gunadi; Endang Setyati
Jurnal Infra Vol 8, No 1 (2020)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

In order to ensure security measures, traffic violations are an important matter. One of the most traffic violations is the use of helmets on motorcycle riders. Therefore, a program was created that could help in identifying helmet users for motorcycle riders. In the process of identifying data, a problem that is often experienced is helmet characteristics. In this study a filter experiment will be conducted in order to recognize the characteristics of the helmet. This study uses 2 methods, You Only Look Once (YOLO) and Convolutional Neural Network (CNN). The YOLO method is used to find regions of motorbikes and motorbike riders. The CNN method is used to classify helmet users in motorcycle riders. The results of the CNN classification will be calculated using a confusion matrix in order to get the accuracy of the correct prediction. The program results from this study will identify helmet users on motorcyclists in the video. Accuracy obtained between motorcycle riders driving with helmets and without helmets is 70.49%.

Pengenalan Alfabet Bahasa Isyarat Tangan Secara Real-Time dengan Menggunakan Metode Convolutional Neural Network dan Recurrent Neural Network Devina Yolanda; Kartika Gunadi; Endang Setyati
Jurnal Infra Vol 8, No 1 (2020)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Sign language is one of the communication tools commonly used by people with disabilities. The alphabet sign language is a basic tool used by teachers to teach people with hearing impairment and speech impairment to recognize basic alphabet letters. However, many people find it difficult to communicate with these groups because of a lack of community insight into hand sign language. Research on sign language has experienced much progress in processing static images but is still experiencing problems due to difficulties in processing dynamic images / video given that most of the sign language is represented by body, hand, and face movements.This study uses Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) methods with video input. The CNN method will be used as a feature extraction in the spatial feature while the RNN is tasked to tolerate between frames extracted by CNN on the temporal feature.The final result to be displayed is in the form of text alphabet which is the result of the recognition of the sign language alphabet. Based on the test carried out, obtained an average accuracy value of 60.58% for all letters while real-time testing has failed because the technology used cannot sustain the architecture created.

Pengembangan Chrome Extension untuk Mengidentifikasi Phishing Website berdasarkan URL dengan Algoritma Random Forest Kevin Benedict; Agustinus Noertjahyana; Endang Setyati
Jurnal Infra Vol 9, No 1 (2021)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

The ever developing technology makes internet one of the most important part in human’s daily activity. This development is also followed by the increase of phishing activity which is not only in quantity, but also in the variety of techniques. The loss caused by phishing attacks is quite big. There are a lot of applications for preventing phishing attacks, but most of them are still not accurate enough. Several studies show that ensemble learning algorithm has a good capability in detecting phishing website.In this research a chrome extension which uses a Random Forest model to detect phishing websites has been developed. Random Forest is one of the most well-known ensemble learning algorithm. The most important hyperparameters which would be experimented with are n_estimators, min_samples_leaf, min_samples_split, max_features, and max_depth. Features used are Lexical features which are based on references from other researches, and Domain-based features which are the newly proposed ones, comprised of Global Page Rank, Average Daily Time, Sites Linking In, Domain Age, and Registration Period. All features are obtained only from the URL.This research shows that dataset quality is the most impacting factor in making a good model. Hyperparameter tuning is also an important part but is only limited to certain scenario. The newly proposed features could make an improvement to the model’s performance. From several experiments, the usage of Lexical and Domain-based features has successfully achieved the best accuracy of 98.28%.

Pengenalan Jenis Bunga Anggrek Menggunakan Metode Color Local Binary Pattern dan Support Vector Machine Debby Meliani Prayogo; Kartika Gunadi; Endang Setyati
Jurnal Infra Vol 8, No 1 (2020)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Orchid flowers are the flowering plants with the most types or species. One of them is the moon orchid flower which is one of the three national flowers in Indonesia. Orchid flowers can be found in city parks and many tourist attractions because of its beauty. However, people will certainly have difficulty in recognizing the type of orchid. Therefore, a program is made to help people in identifying the types of orchids that are around. Orchid flower recognition has already been researched to recognize the texture of its flower. However, this study uses 25 species of orchids that is from Indonesia to be recognized.You Only Look Once (YOLO) method is used for detecting flower objects in the image. Before classifying the orchid species, the background image need to be removed using Image Segmentation. The Color Local Binary Pattern descriptor is used to get the texture of the image through several colorspaces, namely grayscale, RGB, HSI, YIQ, and oRGB. Support Vector Machine is then used to recognize the type of orchid.The result of this program can recognize the species of orchids in the picture. From the test results using the researcher’s dataset show an accuracy of 30.7% using color space grayscale, 37% using color space RGB, 34.6% using color space HSI, 41% using color space YIQ, and 40.2% using color space oRGB in recognizing the species of orchid.

Identifikasi Varietas Koi Berdasarkan Gambar Menggunakan Zero Parameter Simple Linear Iterative Clustering dan Support Vector Machine Amadea Sapphira; Alexander Setiawan; Endang Setyati
Jurnal Infra Vol 8, No 2 (2020)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

There’s currently 120 types of koi fish that has been bred around the world. The types of koi fish depends on the color patterns and shapes they have. There’s alot of patterns that has similarity between one type with another. For example, sanke and showa koi fish will look similar from a non-expert’s point of view, because both type has same color pattern, which is red, black and white. In actuality, sanke koi is dominantly red and white with slight black accent, while showa’s dominant color is red and black, with white accent.In this research, Zero Parameter Simple Linear Iterative Clustering (SLICO) method and Simple Linear Iterative Clustering (SLIC) will be tested and used to process the image segmentation process to eliminate the background of the image. Color Local Binary Pattern method is used to get the textures on images through the RGB, HSV, and grayscale colorspace. Support Vector Machine is used to identify types of koi fish. To test the SVM, two kind of kernel is used, which is linear kernel and Radial Basis Function (RBF) kernel.The results of this study are the program able to recognize types of koi from iamges. The test results show an accuracy of 36% in grayscale colorspace, 50% in RGB colorspace, and 48% in HSV colorspace.

Title

Found 6 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 6 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 6 Documents
Search