Garuda - Garba Rujukan Digital

Classification of Radical Web Content in Indonesia using Web Content Mining and k-Nearest Neighbor Algorithm Subhan, Muh; Sudarsono, Amang; Barakbah, Ali Ridho
EMITTER International Journal of Engineering Technology Vol 5, No 2 (2017)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24003/emitter.v5i2.214

Radical content in procedural meaning is content which have provoke the violence, spread the hatred and anti nationalism. Radical definition for each country is different, especially in Indonesia. Radical content is more identical with provocation issue, ethnic and religious hatred that is called SARA in Indonesian languange. SARA content is very difficult to detect due to the large number, unstructure system and many noise can be caused multiple interpretations. This problem can threat the unity and harmony of the religion. According to this condition, it is required a system that can distinguish the radical content or not. In this system, we propose text mining approach using DF threshold and Human Brain as the feature extraction. The system is divided into several steps, those are collecting data which is including at preprocessing part, text mining, selection features, classification for grouping the data with class label, simillarity calculation of data training, and visualization to the radical content or non radical content. The experimental result show that using combination from 10-cross validation and k-Nearest Neighbor (kNN) as the classification methods achieve 66.37% accuracy performance with 7 k value of kNN method[1].

Classification of Radical Web Content in Indonesia using Web Content Mining and k-Nearest Neighbor Algorithm Muh Subhan; Amang Sudarsono; Ali Ridho Barakbah
EMITTER International Journal of Engineering Technology Vol 5 No 2 (2017)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24003/emitter.v5i2.214

Radical content in procedural meaning is content which have provoke the violence, spread the hatred and anti nationalism. Radical definition for each country is different, especially in Indonesia. Radical content is more identical with provocation issue, ethnic and religious hatred that is called SARA in Indonesian languange. SARA content is very difficult to detect due to the large number, unstructure system and many noise can be caused multiple interpretations. This problem can threat the unity and harmony of the religion. According to this condition, it is required a system that can distinguish the radical content or not. In this system, we propose text mining approach using DF threshold and Human Brain as the feature extraction. The system is divided into several steps, those are collecting data which is including at preprocessing part, text mining, selection features, classification for grouping the data with class label, simillarity calculation of data training, and visualization to the radical content or non radical content. The experimental result show that using combination from 10-cross validation and k-Nearest Neighbor (kNN) as the classification methods achieve 66.37% accuracy performance with 7 k value of kNN method[1].

Classification Freshness of Red Snapper (Lutjanus Campechanus) Based on Eye Image Using Convolutional Neural Network Muh Subhan; Nursakinah Nursakinah
EPI International Journal of Engineering Vol 5 No 1 (2022): Volume 5 Number 1, February 2022
Publisher : Center of Techonolgy (COT), Engineering Faculty, Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25042/epi-ije.022022.08

Indonesia is a maritime country where fish is the most widely extracted and consumed marine natural resource, one of which is snapper. Snapper contains high protein. Therefore, it is suitable for health. Red snapper or Lutjanus campechanus is one economical fish with a broad market share. Red snapper is a demersal fish group that ranks third with the most exported commodities after tuna and shrimp. In addition, snapper is one of the most common consumption fish in Indonesia. Therefore, the community needs to be able to identify the freshness of the fish. Fish freshness detection is done manually by touching the fish's body, eyes, and gills. However, this can cause accidental damage to the fish parts, which will be very detrimental. Several studies on identifying fish freshness explain that the VGGNet-16 Architecture on the Convolutional Neural Network algorithm is superior in its modeling performance. This research uses a different fish object, a red snapper object, with two different architectures from several previous studies, namely the Le-Net15 and VGGNet-16 architecture. This research focuses on the eye image carried out through the pre-processing data stage by cutting the fish body, followed by augmentation to reproduce the image data without losing its essence before training the dataset. The model will be trained using the Adam optimization method with very fresh and not fresh predictions. The experimental results of the classification of two classes of red snapper freshness using 600 fish images show that VGGNet-16 achieves the best performance compared to the LeNet-5 architecture, where the classification accuracy reaches 98.40%.

Klasifikasi Mutu Buah Pala (Myristica Fragrans Houtt) Berbasis Pengolahan Citra Menggunakan Metode Deep Learning Arsitektur Faster R-CNN Subhan, Muh; Basri, Hasan
INTEK: Jurnal Penelitian Vol 6 No 2 (2019): October 2019
Publisher : Politeknik Negeri Ujung Pandang

Fakfak is the number one nutmeg producing area in Indonesia with a land area of around 16,011 Ha. Nutmeg production is projected to continue to increase until 2020, recorded in 2011 the production of nutmeg in particular reached 12,884 tons or 25 percent of the total Indonesian nutmeg production. This increase was not followed by an increase in market share. One solution to get a wider nutmeg market is exports. But currently not all requests for nutmeg can be fulfilled, because the quality of the nutmeg does not meet the requirements requested. One factor is the surface defects in the nutmeg skin that affects the quality of the fruit, especially the appearance of the fruit. The sorting of nutmegs has so far been using conservative methods, namely by observation based on experience (self-taught). This manual method is felt to be less effective because it depends on the conditions and conditions of the sorting staff, different perceptions between each sorter, takes a long time, requires large costs and involves many workers. To deal with these problems, our previous research developed a method for classifying nutmeg seeds, using image processing methods with color and shape parameters combined with a neural network and sigmoid convolution classification algorithm as a validation method, an accuracy of 87%, but this has not been said to be optimal so we try to use the same approach with the latest method improvements using the R-CNN Faster obtained the best accuracy of 95% with a learning rate of 4000 with a processing time of 0.04 minutes per second.

Title

Found 4 Documents
Search

Abstract

Abstract

Abstract

Abstract

Title Search

Found 4 Documents Search

Abstract

Abstract

Abstract

Abstract

Title

Found 4 Documents
Search