Article Per Year (5 Year)
p-Index From 2020 - 2025
2.754
P-Index
This Author published in this journals
All Journal Jurnal Infra
Kartika Gunadi
Program Studi Informatika
Computer Science & IT

Published : 21 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 21 Documents
Search

 1   2   3 
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

Abstract

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

Abstract

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%.
Perbandingan Character Recognition dan Text Recognition Menggunakan Extended MNIST dan IAM Database dan Tesseract pada Tulisan Tangan Ijazah Made Yoga Mahardika; Kartika Gunadi; Alexander Setiawan
Jurnal Infra Vol 8, No 2 (2020)
Publisher : Jurnal Infra

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

Abstract

The problem with handwriting is how a technique can recognize various types of writing in various forms. Different from computer letters that consistent, each human’s handwriting is unique in the form and consistency. These problems can be found in ijazah documents where the data is handwriting.Data location segmentation uses run length smoothing algorithm with dots as segmentation features. Handwritten text recognition (HTR) technique requires data segmented into words. Handwritten character recognition (HCR) technique requires data segmented into characters. HCR uses the LeNet5 model with the EMNIST dataset. HTR uses tesseract tool and convolutional recurrent neural networks with the IAM database.Experiment on 10 samples of scan images, segmentation obtained an average accuracy of 95.6%. The HCR technique failed in the letter segmentation process in cursive handwriting. The best technique is the HTR with tesseract tool managed to get word accuracy above 69% tested on 5 scan samples, 15 data fields.
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

Abstract

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.
Aplikasi Rekomendasi Pengemudi Perusahaan Jasa Travel Bismar Trans dengan Metode Simple Additive Weighting Benediktus Marcelino Pratama; Kartika Gunadi; Alexander Setiawan
Jurnal Infra Vol 8, No 2 (2020)
Publisher : Jurnal Infra

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

Abstract

Bismar Trans Travel Services Company is one of the engaged in transportation. During this time there are internal problems, one of which is the selection of the driver. So there needs to be a solution.This research was conducted to find the best driver. Travel Services Company Bismar Trans as a job provider uses the driver's recommendation application with the Simple Additive Weighting method with the PHP Programming Language, and the MySQL database.The results showed that the system calculation results were in accordance with the company's weight and criteria, the application could provide appropriate recommendations according to the company's needs and from the results of the questionnaire, the program had a good appearance, produced the right results, and had benefits.
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

Abstract

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.
Penerapan Metode YOLO dan Tesseract-OCR untuk Pendataan Plat Nomor Kendaraan Bermotor Umum di Indonesia Menggunakan Raspberry Pi Eric Tirtana; Kartika Gunadi; Indar Sugiarto
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

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

Abstract

Parking system is a common thing to find in public places. Parking system usually comes with a program that enables to detect and read license plates. With the advancement of technology, there are many systems / programs that are able to automatically detect and read license plates, but they come with a costly price. In this research, Raspberry Pi 4 will be used as the main platform. With the usage of Raspberry Pi, it is expected to reduce the cost needed to achieve the same output. However, by using Raspberry Pi, the hardware specifications are not as good as computer in general. In this research YOLO will be used to detect the license plate and Tesseract-OCR is used to read the characters on the license plate. From this research, it can be concluded that program can implement YOLO and Tesseract-OCR to detect and read public transportation license plates while being run on Raspberry Pi 4. To get the optimal results, the input image needs to be taken at daytime, using high quality camera, and implement only the necessary pre-processing methods.
Sistem Pencarian Rute untuk Salesman menggunakan metode Saving Matrix dengan Harmony Search pada Android Lukas Fernando Hunggianto; Kartika Gunadi; Anita Nathania Purbowo
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

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

Abstract

Technology is growing at faster rate. Smartphone usage becomes one of the requirements to do many kinds of things. The majority of smartphone users currently using Android because it has a affordable price. Global Positioning System Technology (GPS) nowadays is easy to use can be applied to many things. One of them is application of tracking device. In the PT. X. , this technology can be used to do product review after-sales. Sales at the PT. X has a job that has been given by their supervisor to do product identification for their installed GPS device. This product that need to be identified is widely spread in Indonesia. For this research, they are using perfected saving matrix method using harmony search to produce short distance travel. At testing it will be compared between only saving matrix, harmony search, and both of the saving matrix and harmony search. The results obtained all the features can run well. The route calculation using the saving matrix method with harmony search gets test results in area 1 with 34 destination points, the average saving is 4.163%, while in area 2 with 38 destination points, the average savings is 1.789%.
Sistem Pakar Pendiagnosa Infeksi Saluran Pernafasan Akut (ISPA) dengan Metode Forward Chaining dan Certainty Factor Samuel Njoo; Kartika Gunadi; Henry Novianus Palit
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

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

Abstract

Acute Respiratory Infection (ARI) is a group of diseases that are quite common in developing countries, including Indonesia. ARI consists of various diseases and has a very varied possibility of symptoms. If not detected and treated immediately, ARI can get even worse and can lead to death. With an expert system, users can quickly self-diagnose without worrying about the cost or time required. The knowledge possessed by the expert system also comes from doctors in their fields.The expert system will be built with the help of 2 (two) methods, namely the forward chaining as an inference method and the certainty factor as the calculation method. With the forward chaining method, the system can provide information such as what disease the user is suffering from directly after the user fills all the questions that will be asked by the system. In addition, with the certainty factor method, the system can provide information like how sure the system in providing diagnostic results and is intended in the form of a percentage, the user is also presented with several answer choices so each user's answer choices will have an impact on the final diagnosis result by the expert system.The system will be tested by 3 related experts and the accuracy of system diagnosis is 75%.
Implementasi Convolutional Neural Network untuk Mengetahui Buah Tomat yang Matang pada Pohon Tomat Menggunakan Perangkat Android Timothy Christian Yunanto; Kartika Gunadi; Anita Nathania Purbowo
Jurnal Infra Vol 8, No 1 (2020)
Publisher : Jurnal Infra

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

Abstract

The development of instant era makes people want something that fast and efficient. As we know, picking ripe tomatoes on the tree requires a long time if done by humans. To solve these problems, automatic robots are used that can replace the role of humans. To get a successful automated robot requires the creation of efficient algorithm function (program). The Program can be run on an Android Device. We use Blob Detection method on Computer Vision, and the result will be processed by the Convolutional Neural Network method. CNN method requires to determine whether the object is ripe tomatoes or other objects. Blob Detection is used to detect tomato objects based on previously obtained masks. Before doing the training, it is necessary to make a model that contains convolutional layer, max polling layer, flatten layer, dropout layer, and dense layer. The test is carried out with a scenario study and several cases such as bunched tomatoes, scattered tomatoes, tomatoes whose masks are not oval, and so on. The results show that the results of CNN are very dependent on the results of Blob Detection because the input from CNN is from the result of Blob Detection. If Blob Detection fails to get the tomato object, CNN will not run properly. The results show that Blob Detection will fail to detect the tomato object if the tomato is blocked by another object which causes the mask shape of the object to be chaotic. The test results from CNN also showed an accuracy value of training of 96% and testing accuracy of 93%.
Co-Authors Albert Albert Alexander Setiawan Alexander William Sutjiadi Alvin Nathaniel Tjondrowiguno Anita Nathania Purbowo Benediktus Marcelino Pratama Debby Meliani Prayogo Devina Yolanda Endang Setyati Endang Setyati Eric Tirtana Handy Prayoga Angjaya Henry Novianus Palit Indar Sugiarto Jonathan Adiwibowo Kevin Kevin Leo Willyanto Santoso Liliana Liliana Lily Puspa Dewi Lucky Alexandre Lembangan Lukas Fernando Hunggianto Made Yoga Mahardika Martina Marcelline Taslim Richard Lawrence Thiosdor Ricky Herwanto Ricky Setiawan Saswono Rudi Adipranata Rudy Adipranata Samuel Njoo Silvia Rostianingsih Susangto Andi Putera S. Timothy Christian Yunanto Yoel Andreas Zachary Osborn