Krisdianto

@ulm.ac.id

Mathematics and Natural Sciences Faculty
Lambung Mangkurat University

Krisdianto


            Download Compact PDF  
https://researchid.co/krisdianto
Currently, an associate professor at Biological Study Program, at Mathematics and Natural Sciences Faculty (MIPA), Lambung Mangkurat University. Has been worked as a lecturer, researcher, and social empowerment for about 34 years.

EDUCATION

1. Undergraduate: Institut Teknologi Bandung, Indonesia, (Biology, Ecology)
2. Postgraduate: Napier University of Edinburgh, Scotland UK (Biological water resource management)
3. Doctoral: Universitas Brawijaya, Indonesia (Natural resource and environmental management), Indonesia

RESEARCH INTERESTS

Urban and Wetland Ecology, Biodiversity, Environment
1

Scopus Publications

Scopus Publications

  • Wood Identification on Microscopic Image with Daubechies Wavelet Method and Local Binary Pattern
    Salma, P. H. Gunawan, Esa Prakasa, Bambang Sugiarto, Riyo Wardoyo, Yan Rianto, Ratih Damayanti, Krisdianto, Listya Mustika Dewi
    2018 International Conference on Computer Control Informatics and Its Applications Recent Challenges in Machine Learning for Computing Applications Ic3ina 2018 Proceeding, 2018
    Wood is one of Indonesia’s very rich natural resources abundant because the number reaches around 4,000 species. The process of identifying wood species currently it is still done manually in a relatively long time by observing types of fibers, vessels, rays, and other structures directly because there is not a much automatic application of identification of wood species is made. This is an obstacle for experts anatomy of wood because it must check wood species accurately and quickly. Therefore that, the field of Computer Vision is the right solution to develop the process Identification of wood species automatically. In this research program will be made application of Computer Vision to identify wood species with using the Daubechies Wavelet (DW) and Local Binary Pattern (LBP) methods for The extraction of the wood pattern is then classified Support Vector Machine (SVM) method. Results obtained in this study is able to identify the microscopic image of wood as a species of wood with average SVM accuracy is 85%.