Eko Hari Rachmawanto
Dian Nuswantoro University

Published : 10 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Bulletin of Electrical Engineering and Informatics

Orchid types classification using supervised learning algorithm based on feature and color extraction Pulung Nurtantio Andono; Eko Hari Rachmawanto; Nanna Suryana Herman; Kunio Kondo
Bulletin of Electrical Engineering and Informatics Vol 10, No 5: October 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v10i5.3118

Abstract

Orchid flower as ornamental plants with a variety of types where one type of orchid has various characteristics in the form of different shapes and colors. Here, we chosen support vector machine (SVM), Naïve Bayes, and k-nearest neighbor algorithm which generates text input. This system aims to assist the community in recognizing orchid plants based on their type. We used more than 2250 and 1500 images for training and testing respectively which consists of 15 types. Testing result shown impact analysis of comparison of three supervised algorithm using extraction or not and several variety distance. Here, we used SVM in Linear, Polynomial, and Gaussian kernel while k-nearest neighbor operated in distance starting from K1 until K11. Based on experimental results provide Linear kernel as best classifier and extraction process had been increase accuracy. Compared with Naïve Bayes in 66%, and a highest KNN in K=1 and d=1 is 98%, SVM had a better accuracy. SVM-GLCM-HSV better than SVM-HSV only that achieved 98.13% and 93.06% respectively both in Linear kernel. On the other side, a combination of SVM-KNN yield highest accuracy better than selected algorithm here.
Triple layer image security using bit-shift, chaos, and stream encryption Ajib Susanto; De Rosal Ignatius Moses Setiadi; Eko Hari Rachmawanto; Ibnu Utomo Wahyu Mulyono; Christy Atika Sari; Md Kamruzzaman Sarker; Musfiqur Rahman Sazal
Bulletin of Electrical Engineering and Informatics Vol 9, No 3: June 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (851.826 KB) | DOI: 10.11591/eei.v9i3.2001

Abstract

One popular image security technique is image encryption. This research proposes an image encryption technique that consists of three encryption layers, i.e. bit-shift encryption, chaos-based encryption, and stream encryption. The chaos algorithm used is Arnold's chaotic map, while the stream cipher algorithm used is RC4. Each layer has different cryptology characteristics in order to obtain safer image encryption. The characteristics of cryptology are permutation, confusion, diffusion, and substitution. The combination of the proposed encryption method aims to secure images against various attacks, especially attacks on statistics and differentials. The encryption method testing is done by various measuring instruments such as statistical analysis, i.e. entropy information, avalanche effect, and histogram, differential analysis, i.e. UACI and NPCR, visual analysis using PSNR and SSIM, and bit error ratio. Based on the results of experiments that the encryption method that we propose can work excellently based on various measurement instruments. The decryption process can also work perfectly this is evidenced by the ∞ value based on PSNR, and zero value based on SSIM and BER.