R. V. Hari Ginardi

Sugarcane leaf disease detection and severity estimation based on segmented spots image

About 15% of sugarcane leaf is defective because of diseases, it reduces the quantity and quality of sugarcane production significantly. Early detection and estimation of plant disease is a way to control these diseases and minimize the severe infection. This paper proposes a model to identify the severity of certain spot disease which appear on leaves based on segmented spot. The segmented spot is obtained by thresholding a* component of L*a*b* color space. Diseases spots are extracted with maximum standard deviation of segmented spot that use for detection the type of disease using classification techniques. The classifier is a Support Vector Machine (SVM) which uses L*a*b* color space for its color features and Gray Level Co-Occurrence Matrix (GLCM) as its texture features. This proposed model capable to determine the types of spot diseases with accuracy of 80% and 5.73 error severity estimation average.

Color correction using improved linear regression algorithm

Color correction is one of essential stages in image processing, which plays an important role during image acquisition or pre-processing to produce a better color quality, before being used in further process. This paper proposes a new method for color correction using an improved linear regression algorithm based on a stepwise model. This proposed method is designed for assessing a series of discrete color levels, for instance in a leaf color chart. Color chart as a reference image is used for controlling color levels of a captured image or calibrating the image sensor. The experiment is conducted in L*a*b* color space, therefore a transformation from RGB into L*a*b* is needed at the first phase. The best matched color level between reference and captured image will be selected by k-Means clustering method. Chosen color levels are used for constructing linear regression function. This function is applied as well for removing outlier among color levels. To ensure the result of this color correction does not depend on lighting condition, the color constancy algorithm is acquired. Gray World and White Patch are chosen for color constancy methods. Compared to ordinary linear regression and color correction without adding color constancy, the combination of Gray World and improved linear regression algorithm based on stepwise model shows the best result in almost entire datasets in various lighting conditions.

Enhancing tomato clustering evaluation using color correction with improved linear regression in preprocessing phase

Color inconsistency poses many difficulties when capturing the same object using different image capture devices. Color is one of main parts in image preprocessing and therefore color correction is needed to calibrate images in order to produce consistent color values. In this paper, we propose a new color correction method by employing combined linear regression with stepwise model to enhance the quality of tomatoes ripeness clustering. Macbeth ColorChecker is needed as a reference image while a test image to be corrected is captured by an Android smartphone camera. There are 12 color levels to be compared between reference and test image. However, only a number of color levels are selected by k-means clustering. The selected color levels are utilized to build a linear regression algorithm with stepwise model. The result confirms that color correction and color constancy increase the clustering performance by 10% up to 40% for all possible configurations.

Intelligent Method for Dipstick Urinalysis Using Smartphone Camera

This paper introduces an intelligent method for helping people to maintain their healthy by doing a self urinalysis utilising a smartphone camera. A color sensing method using a smartphone camera is designed to determine the value of a reagent strip in a urinalysis dipstick. In the dipstick urinalysis, a color change in each reagent strip is examined. This color change is a result of the reaction of dipstick to the chemical contents of urine including pH, Protein, Glucose, Ketones, Leucocyte, Nitrite, Bilirubine, and Urobilinogen. Performing disptick urinalysis can be done in almost any places even on the very remote area where medical laboratory cannot be found, and it is much easier and cheaper than medical lab visit.

Implementasi Metode K-Nearest Neighbor Untuk Penentuan Lokasi Pos Hujan Terdekat Dengan Titik Rute Perjalanan Pada Aplikasi Clearroute

Clearroute adalah aplikasi yang dibangun untuk memudahkan seseorang mengetahui informasi cuaca pada rute perjalanan yang akan dilaluinya. Aplikasi ini dibangun untuk platform perangkat bergerak yang memiliki fungsi-fungsi untuk memudahkan seseorang mencari informasi cuaca untuk perjalanannya.Pada aplikasi perangkat bergerak tersebut, diperlukan sebuah sistem web service yang dapat melakukan pengolahan data. Seperti pengolahan data untuk menentukan lokasi pos hujan terdekat dengan rute perjalanan pengguna. Pengolahan data untuk mendapatkan kondisi cuaca dan kondisi ramalan cuaca yang akan datang. Oleh karena itu dibutuhkanlah suatu sistem yang dapat memenuhi fungsi tersebut agar aplikasi yang dibangun dapat bekerja dengan baik,Pada sistem yang dibangun ini digunakan algoritma K-Nearest Neighbor untuk menentukan klasifikasi cuaca yang dimiliki oleh rute yang akan dilalui oleh pengguna. Kemudian sistem ini memanfaatkan Laravel 5.4 sebagai kerangka kerja pemrograman.Pengujian pada sistem ini dilakukan dengan cara melakukan permintaan informasi cuaca kepada sistem, mencoba melakukan ekstraksi data cuaca dari BMKG.Pengujian tersebut dilakukan untuk mengetahui keberhasilan sistem dalam menangani permintaan dan pengolahan data yang diminta oleh aplikasi perangkat bergerak Clearroute. Dari hasi pengujian, sistem yang telah dirancang dan diimplementasikan telah memenuhi segala kebutuhan pengolahan data pada aplikasi Clearroute

Rekomendasi Indekos dengan Metode Pembobotan pada Aplikasi E-Commerce CariKos Berbasis Web

CariKos merupakan aplikasi e- commerce berbasis web yang dapat membantu dalam pencarian indekos. CariKos dapat membantu pemilik indekos memasarkan indekosnya. Selain itu, pencari indekos dapat mencari indekos sesuai dengan keinginannya dan melakukan transaksi pada aplikasi. Agar pencari mendapatkan indekos yang tepat, CariKos menyediakan fitur rekomedasi indekos menggunakan metode pembobotan. Metode pembobotan tersebut digunakan untuk mendapatkan nilai dari indekos. Nilai indekos didapatkan dari delapan nilai kriteria. Setiap kriteria memiliki nilai bobot persen masing-masing. Untuk mendapat bobot persen, digunakan Analytical Hierarchy Process . Tahap pengujian dilakukan dengan pendaftaran indekos dan pencarian indekos. Pencarian indekos dilakukan untuk melihat ketertarikan pengguna terhadap indekos yang direkomendasikan. Hasil pengujian menunjukkan bahwa 93.8% partisipan tertarik dengan indekos yang direkomendasikan.

Substation placement optimization method using Delaunay Triangulation Algorithm and Voronoi Diagram in East Java case study

In anticipation of the growth of electricity demand in the region, required the addition of new substations and the development of substation-substation that has operated previously. State Electricity Company developed a plan to determine the number, capacity and location of the substation in order to reconcile the needs of electric current with future electricity needs. This plan requires the identification of the electrical load in each region as well as the capability development of substations existing substations. Expenses allocated to a substation based on the distance between them by seeking the minimum transportation cost. Cost is optimized for all of the substation through the allocation of the burden to the appropriate substation. This final project is aimed at optimizing and find the service area (service area) by APJ by applying Voronoi diagram and Delaunay Triangulation.

Sugarcane variety identification using Dynamic Weighted Directed Acyclic Graph Similarity

Dynamic wDAG Similarity algorithm can be applied to sugarcane annotation. At first, we have to make a wDAG structure of many different varieties of sugarcane. We also have to make wDAG of sugarcane that will be annotated. Then, we have to calculate the similarity between wDAG types of sugarcane that will be annotated and wDAG of all the existing types of sugarcane. This similarity calculation results will present sequence similarities ranging from the most similar to the most distant from sugarcane varieties were annotated. This Dynamic wDAG Similarity algorithm has difference compared with the previous wDAG Similarity algorithm. WDAG used in this research has the node labeled, arc labeled and arc weighted, where the weight of the arc can be changed dynamically. This research fixes the previous studies of static wDAG, in which the weight values on the arc of wDAG can not be changed. On Dynamic wDAG, the weight on each arc is based on the fuzzy calculations that show the tendency of sugarcane varieties were annotated. And the fuzzy value is calculated based on agronomic traits of sugarcane to be annotated. Leaf node is the part of wDAG that will be compared first. The similarity calculation result between the two wDAG is affected by data on a leaf node to be compared and the weights of the arcs. The result shows that this method gained the average of Precision of 96%, the average of Recall of 88.5%, and the average of Accuracy of 96%.

Identification of oil palm plantation in IKONOS images using radially averaged power spectrum values

The use of satellite imagery for plantation management is helpful in monitoring the development of various parties including oil palm plantations. In a panchromatic IKONOS satellite imagery, oil palm plantations have unique characteristics that can be interpreted visually. This study tried to classify oil palm plantations from satellite imagery using texture characteristics with their spatial and frequency parameters. Spatial parameters are determined by calculating the first order features, while the second order texture variables are determined based on Gray Level Co-occurrence Matrix (GLCM), local feature, and Radially Average Power Spectrum Value (RAPSV). The classification accuracy of of this study reached 86%. An addition of average value of the power spectrum has increased the accuracy up to 28% compared to the usage of first order only.

Feature extraction for identification of sugarcane rust disease

This research propose an image pattern classification to identify rust disease in sugarcane leaf with a combination of texture and color feature extraction. The purpose of this research is to find appropriate features that can identify sugarcane rust disease. Firstly, normal and diseased images are collected and pre-processed. Then, features of shape, color and texture are extracted from these images. After that, these images are classified by support vector machine classifier. A combination of several features are used to evaluate the appropriate features to find distinctive features for identification of rust disease. When a single feature is used, shape feature has the lowest accuracy of 51% and texture feature has the highest accuracy of 96.5%. A combination of texture and color feature extraction results a highest classification accuracy of 97.5%. A combination of texture and color feature extraction with polynomial kernel results in 98.5 % classification accuracy.