Kohei Arai
Graduate School of Science and Engineering, Saga University, Saga City, Japan

Published : 5 Documents
Articles

Found 5 Documents
Search

A Computer Aided System for Tropical Leaf Medicinal Plant Identification Herdiyeni, Yeni; Nurfadhilah, Elvira; Zuhud, Ervizal A.M.; Damayanti, Ellyn K.; Arai, Kohei; Okumura, Hiroshi
International Journal on Advanced Science, Engineering and Information Technology Vol 3, No 1 (2013)
Publisher : International Journal on Advanced Science, Engineering and Information Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (475.102 KB) | DOI: 10.18517/ijaseit.3.1.270

Abstract

The objective of this paper is to develop a computer aided system for leaf medicinal plant identification using ProbabilisticNeural Network. In Indonesia only 20-22% of medicinal plants have been cultivated. Generally, identification process of medicinalplants has been done manually by a herbarium taxonomist using guidebook of taxonomy/dendrology. This system is designed to helptaxonomist to identify leaf medicinal plant automatically using acomputer-aided system. This system uses three features of leaf toidentify the medicinal plant, i.e., morphology, shape, and texture. Leaf is used in this system for identification because easily to find.To classify medicinal plant we used Probabilistic Neural Network. The features will be combined using Product Decision Rule (PDR).The system was tested on 30 species medicinal plant from Garden of Biopharmaca Research Center and Greenhouse Center of Exsitu Conservation of Medicinal Indonesian Tropical Forest Plants, Faculty of Forestry, Bogor Agriculture University, Indonesia.Experiment results showed that the accuracy of medicinal plant identification using combination of leaf features increase until74,67%.The comparative analysis of leaf features has been performed statistically. It showed that shape is a dominant features for plant identification. This system is very promising to help people identify medicinal plant automatically and for conservation and utilization of medicinal plants.
Centronit: Initial Centroid Designation Algorithm for K-Means Clustering Barakbah, Ali Ridho; Arai, Kohei
EMITTER International Journal of Engineering Technology Vol 2, No 1 (2014)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24003/emitter.v2i1.17

Abstract

Clustering performance of the K-means highly depends on the correctness of initial centroids. Usually initial centroids for the K- means clustering are determined randomly so that the determined initial centers may cause to reach the nearest local minima, not the global optimum. In this paper, we propose an algorithm, called as Centronit, for designation of initial centroidoptimization of K-means clustering. The proposed algorithm is based on the calculation of the average distance of the nearest data inside region of the minimum distance. The initial centroids can be designated by the lowest average distance of each data. The minimum distance is set by calculating the average distance between the data. This method is also robust from outliers of data. The experimental results show effectiveness of the proposed method to improve the clustering results with the K-means clustering.Keywords: K-means clustering, initial centroids, Kmeansoptimization.
Centronit: Initial Centroid Designation Algorithm for K-Means Clustering Barakbah, Ali Ridho; Arai, Kohei
EMITTER International Journal of Engineering Technology Vol 2, No 1 (2014)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

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

Abstract

Clustering performance of the K-means highly depends on the correctness of initial centroids. Usually initial centroids for the K- means clustering are determined randomly so that the determined initial centers may cause to reach the nearest local minima, not the global optimum. In this paper, we propose an algorithm, called as Centronit, for designation of initial centroidoptimization of K-means clustering. The proposed algorithm is based on the calculation of the average distance of the nearest data inside region of the minimum distance. The initial centroids can be designated by the lowest average distance of each data. The minimum distance is set by calculating the average distance between the data. This method is also robust from outliers of data. The experimental results show effectiveness of the proposed method to improve the clustering results with the K-means clustering.Keywords: K-means clustering, initial centroids, Kmeansoptimization.
EYE-BASED HUMAN-COMPUTER INTERACTION (HCI): A NEW KEYBOARD FOR IMPROVING ACCURACY AND MINIMIZING FATIGUE EFFECT Mardiyanto, Ronny; Arai, Kohei
Kursor Vol 6, No 3 (2012)
Publisher : University of Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v6i3.1101

Abstract

EYE-BASED HUMAN-COMPUTER INTERACTION (HCI): A NEW KEYBOARD FOR IMPROVING ACCURACY AND MINIMIZING FATIGUE EFFECT aRonny Mardiyanto, bKohei Arai a Electrical Engineering Dept. Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia b Saga University, Japan E-Mail: a ronny_mardiyanto@yahoo Abstrak Permasalahan penggunaan keyboard dengan kendali mata adalah tingkat akurasi, kecepatan yang rendah, dan kesulitan dalam menggunakan tombol kombinasi. Penggunaan sistem Interaksi Komputer Manusia (IKM) berbasis mata dalam jangka waktu yang lama dapat menyebabkan kelelahan. Pada penelitian ini diusulkan keyboard baru dengan sifat bergerak. Keyboard yang diusulkan terdiri dari dua bagian yaitu bagian utama (bersifat bergerak, dapat digerakkan oleh pengguna menggunakan mata dalam proses pemilihan hurufnya) dan bagian pengendali gerak (terdiri dari lima tombol besar yang transparan, digunakan untuk mengendalikan gerak keyboard bagian utama). Metode pendeteksi keberadaan pengguna digunakan untuk mengurangi kelelahan. Penambahan tombol shortcut pada layout utama memungkinkan pengguna melakukan fungsi khusus. Keyboard baru ini memiliki kelebihan diantaranya memiliki tingkat akurasi yang tinggi, lebih cepat dalam melakukan pengetikan, memiliki ukuran yang lebih kecil, memungkinkan pengguna menggunakan fungsi tombol kombinasi, dan dapat meminimalkan efek kelelahan saat pengguna menggunakan sistem IKM berbasis mata dalam jangka waktu yang lama. Hasil pengujian yang dilakukan membuktikan bahwa keyboard ini memilki tingkat akurasi yang lebih baik (92.26%) dibandingkan keyboard jenis tetap (78.57%). Juga, dalam melakukan pengetikan 14 huruf keyboard ini lebih cepat (134.69 detik) dibandingkan keyboard jenis tetap (210.28 detik). Pada pengukuran efek kelelahan menggunakan alat Electro Enchephalo Graf (EEG), keyboard ini lebih dapat meminimalkan efek kelelahan dibandingkan keyboard jenis tetap. Kata kunci: Keyboard Bergerak, Sistem IKM Berbasis Mata, Akurasi, Kecepatan, Kelelahan. Abstract The current problems of keyboard on eye-based Human Computer Interaction (HCI) are accuracy, typing speed, fatigue, and the use of combination keys. We propose a new keyboard consist of two parts: the moveable layout and the navigator keys (fixed and transparent). The user appearance detection method is used for reducing the fatigue effect. The adding shortcut keys to the main layout allowing user executes a special functions through combination keys. The new keyboard has advantages on high accuracy, fast, allowing combination keys, and could minimize fatigue effect. The experiment results show that the new keyboard could achieve better accuracy (92.26%) compared to the fixed keyboard (78.57%). Also, the new keyboard improved accuracy 134.69% than the fixed keyboard(210.28%) when used for typing fourteen character over eye-based HCI. Moreover, we measured the fatigue effect by using Electro Encephalo Graph (EEG) over both methods and the result shows that the new keyboard could minimize fatigue better than the fixed keyboard. By implementing the new keyboard on real eye-based HCI, user could type characters easily, fastly, and no burdened with fatigue effect. Keywords: Keyboard, Eye-based HCI, Accuracy, Typing Speed, Fatigue.
Centronit: Initial Centroid Designation Algorithm for K-Means Clustering Barakbah, Ali Ridho; Arai, Kohei
EMITTER International Journal of Engineering Technology Vol 2 No 1 (2014)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24003/emitter.v2i1.17

Abstract

Clustering performance of the K-means highly depends on the correctness of initial centroids. Usually initial centroids for the K- means clustering are determined randomly so that the determined initial centers may cause to reach the nearest local minima, not the global optimum. In this paper, we propose an algorithm, called as Centronit, for designation of initial centroidoptimization of K-means clustering. The proposed algorithm is based on the calculation of the average distance of the nearest data inside region of the minimum distance. The initial centroids can be designated by the lowest average distance of each data. The minimum distance is set by calculating the average distance between the data. This method is also robust from outliers of data. The experimental results show effectiveness of the proposed method to improve the clustering results with the K-means clustering.Keywords: K-means clustering, initial centroids, Kmeansoptimization.