cover
Contact Name
Mustakim
Contact Email
Mustakim
Phone
-
Journal Mail Official
ijaidm@uin-suska.ac.id
Editorial Address
-
Location
Kab. kampar,
Riau
INDONESIA
Indonesian Journal of Artificial Intelligence and Data Mining
ISSN : 26143372     EISSN : 26146150     DOI : -
Core Subject : Science,
Indonesian Journal of Artificial Intelligence and Data Mining (IJAIDM) is an electronic periodical publication published by Puzzle Research Data Technology (Predatech) Faculty of Science and Technology UIN Sultan Syarif Kasim Riau, Indonesia. IJAIDM provides online media to publish scientific articles from research in the field of Artificial Intelligence and Data Mining. IJAIDM will be published 2 (two) times a year, in March and September, each edition contains 7 (seven) articles. Articles may be written in English or Indonesia.
Arjuna Subject : -
Articles 61 Documents
Evaluation of F-Measure and Feature Analysis of C5.0 Implementation on Single Nucleotide Polymorphism Calling Lailan Sahrina Hasibuan; Sita Nabila; Nurul Hudachair; Muhammad Abrar Istiadi
Indonesian Journal of Artificial Intelligence and Data Mining Vol 1, No 1 (2018): March 2018
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (566.185 KB) | DOI: 10.24014/ijaidm.v1i1.4616

Abstract

Data growing in molecular biology has increased rapidly since Next-Generation Sequencing (NGS) technology introduced in 2000, the latest technology used to sequence DNA with high throughput. Single Nucleotide Polymorphism (SNP) is a marker based on DNA which can be used to identify organism specifically. SNPs are usually exploited for optimizing parents selection in producing high-quality seed for plant breeding. This paper discusses SNP calling underlying NGS data of cultivated soybean (Glycine max [L]. Merr) using C5.0, an improved rule-based algorithm of C4.5. The evaluation illustrated that C5.0 is better than the other rule-based algorithm CART based on f-measure. The value of f-measure using C5.0 and CART are 0.63 and 0.58. Besides of that, C5.0 is robust for imbalanced training dataset up to 1:17 but it is suffer in large training dataset. C5.0’s performance may be increased by applying bagging or the other ensemble technique as improvement of CART by applying bagging in final decision. The other important thing is using appropriate features in representing SNP candidates. Based on information gain of C5.0, this paper recommends error probability, homopolymer left, mismatch alt and mean nearby qual as features for SNP calling.
Random Forest Algorithm for Prediction of Precipitation Aji Primajaya; Betha Nurina Sari
Indonesian Journal of Artificial Intelligence and Data Mining Vol 1, No 1 (2018): March 2018
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (443.435 KB) | DOI: 10.24014/ijaidm.v1i1.4903

Abstract

Predicting rainfall needs to be done as one of such effort to anticipate water flooding. One of the algorithm that can be used to predict rainfall is random forest. The porpose of the research is to create a model by implementing random forest algorithm. The research method consist of four steps: data collection, data processing, random forest implementation, analysis. Random forest implementation with using training set resulted model that has accurracy 71,09%, precision 0.75, recall 0.85, f-measure 0.79, kappa statistic 0.33, MAE 0.35, RMSE 0.46, ROC Area 0.78. Implementation of random forest algorithm with 10-fold cross validation resulted the output with accurracy 99.45%, precision 0.99, recall 0.99, f-measure 0.99, kappa statistic 0.99, MAE 0,09, RMSE 0.14, ROC area 1.
A Gray-Level Dynamic Range Modification Technique for Image Feature Extraction Using Fuzzy Membership Function Arief Bramanto Wicaksono Putra; Rheo Malani; Mulyanto Mulyanto
Indonesian Journal of Artificial Intelligence and Data Mining Vol 1, No 1 (2018): March 2018
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (734.317 KB) | DOI: 10.24014/ijaidm.v1i1.4599

Abstract

The features of an image must be unique so it is necessary to use certain techniques to ensure them. One of the common techniques is to modify the gray dynamic range of an image. In principle, the gray level dynamic range modification maps the gray level ranges from the input image to the new gray level range as an output image using a specific function. Fuzzy Membership Function (MF) is one kind of membership function that applies the Fuzzy Logic concept. This study uses Trapezoidal MF to map the gray dynamic range of each RGB component to produce a feature of an RGB image. The aim of this study is how to ensure the uniqueness of image features through the setting of Trapezoidal MF parameters to obtain the new dynamic range of gray levels that minimize the possibility of other features other than the selected feature. To test the performance of the proposed method, it also tries to be applied to the signature image. Mean Absolute Error (MAE) calculations between feature labels are performed to test authentication between signatures. The results obtained are for comparison of samples of signature images derived from the same source having a much smaller MAE than the comparison of samples of signature images originating from different sources.
The Map-Based Shortest Route Selection by Using Ant Colony Optimization Algorithm Gaffar, Achmad Fanany Onnilita; Wajiansyah, Agusma; Supriadi, Supriadi
Indonesian Journal of Artificial Intelligence and Data Mining Vol 1, No 1 (2018): March 2018
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v1i1.4600

Abstract

The shortest path problem is one of the optimization problems where the optimization value is a distance. In general, solving the problem of the shortest route search can be done using two methods, namely conventional methods and heuristic methods. The Ant Colony Optimization (ACO) is the one of the optimization algorithm based on heuristic method. ACO is adopted from the behavior of ant colonies which naturally able to find the shortest route on the way from the nest to the food sources. In this study, ACO is used to determine the shortest route from Bumi Senyiur Hotel (origin point) to East Kalimantan Governor's Office (destination point). The selection of the origin and destination points is based on a large number of possible major roads connecting the two points. The data source used is the base map of Samarinda City which is cropped on certain coordinates by using Google Earth app which covers the origin and destination points selected. The data pre-processing is performed on the base map image of the acquisition results to obtain its numerical data. ACO is implemented on the data to obtain the shortest path from the origin and destination point that has been determined. From the study results obtained that the number of ants that have been used has an effect on the increase of possible solutions to optimal. The number of tours effect on the number of pheromones that are left on each edge passed ant. With the global pheromone update on each tour then there is a possibility that the path that has passed the ant will run out of pheromone at the end of the tour. This causes the possibility of inconsistent results when using the number of ants smaller than the number of tours.
Classification of Pineapple Fruit Comosus Merr (Nanas) Quality Using Learning Vector Quantization Method Efendi, Muhamad; Defit, Sarjon; Nurcahyo, Gunadi Widi
Indonesian Journal of Artificial Intelligence and Data Mining Vol 4, No 1 (2021): March 2021
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v2i2.4621

Abstract

The demands of publics for these fruits Ananas Comosus Merr (Pineapple) became higher years to years because of the fruit has so many virtues for human healthy and the taste of this fruit is sweet and fresh. Therefore the pineapple farmers have to protect the quality and quantity of this plant in order to get high produce. This research help the pineapple farmers to classify to quality of pineapple fruits by using neural network with Learning Vector Quantization method which has 2 classes, such as: First quality (1st) and Second quality (2nd) quality. This method has 2 process they are : training process and testing process. To input data in the training and testing process are using uniformity, characteristic of varieties, the rate of aging, hardness, size, stem, crown, manure, destroyer, spoilage, rotten and the total solid content of the least was taken by observed the crop of pineapple farmers in the Teluk Batil village Sungai Apit district Siak Riau province. Learning Vector Quantization method automatically will classify the pineapple into their class. The result of the testing classification has gotten the accuracy 65.56% for the first (1st) quality and 34.44% for the second (2nd) quality. At the second testing has gotten 66.67% the accuracy for the first (1st) quality and 33.33% for the second (2nd) quality. At the third (3rd) testing has gotten 64.44% the accuracy for first (1st) quality and 35.56% for the second (2nd) quality.
Data Train Reduction on Data Image With K Support Vector Nearest Neighbor (Case Study : Maize Leaf Image) Marlinda Vasty Overbeek; Yampi R Kaesmetan
Indonesian Journal of Artificial Intelligence and Data Mining Vol 3, No 2 (2020): Spetember 2020
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v3i2.10451

Abstract

In this study, we applied the K Support Vector Nearest Neighbor algorithm to reduce data train on data image. The data image that we used is the maize leaves image infected with fungi and healthy maize leave. The aim of data train reduction in this study is to get faster and more accurate prediction results. This because by using the K Support Vector Nearest Neighbor algorithm, a support vector that is formed from the algorithm really characterize the objective function of the problem. The accuracy obtained from this study is 0.20 or 20% mean error for the value of nearest neighbor K  = 3 and using K Nearest Neighbor as a model construction algorithm. The error value is smaller than when we compared to the construction of the model without performing data train reduction. The error value if not doing any reduction is 0.209 or 20.9%. Whereas in terms of time efficiency, working with the K Support Vector Nearest algorithm is 24 seconds faster than without performing data train reduction 
Implementation of Data Mining to Predict The Feasibility of Blood Donors Using C4.5 Algorithm Anita Febriani; Tiara Trimadya Rahmawati; Eka Sabna
Indonesian Journal of Artificial Intelligence and Data Mining Vol 1, No 1 (2018): March 2018
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (367.044 KB) | DOI: 10.24014/ijaidm.v1i1.4562

Abstract

Blood Transfusion Unit PMI Pekanbaru City is part of a company or agency that serves blood donation, every blood bag obtained from the community voluntarily come to PMI to donate blood with the goal of humanity. In Blood Transfusion Unit PMI Pekanbaru City, has provisions to be blood donors that must be met in order to donate blood in UTD PMI Pekanbaru City. Data Mining is a combination of a number of computer science disciplines that are defined as the process of discovering new patterns from massive data sets. By using RapidMiner software and using the method of Decision Tree Algorithm C4.5 to determine the eligibility of blood donors based on Age, Weight, Hemoglobin, and Blood Pressure. In the study of hemoglobin is the most decisive variable in blood donors. And the result accuracy is 94.02% which means the accuracy of this model is very good.
Implementation of Backpropagation Neural Network to Detect Suspected Lung Disease Fadhilah Syafria; Boni Iqbal; Elvia Budianita; Iis Afrianty
Indonesian Journal of Artificial Intelligence and Data Mining Vol 1, No 1 (2018): March 2018
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (519.707 KB) | DOI: 10.24014/ijaidm.v1i1.5023

Abstract

Many People were less concerned with lung health, it caused people identified as suffering from lung diseases. Early symptoms that often appear  was cough that took a long time and could be the beginning of more severe disease. Therefore it was necessary to create application that could detect suspected person contracted lung disease. The applications were made by using artificial neural network with Backpropagation with initial input data, symptoms by patients of lung diseases. The symptoms were 22, and kind of lung diseases as a diagnosis were asthma, pneumonia, pulmonary tuberculosis and lung cancer. It used medical records of lung disease as much as 110 data. Network training uses 3 different architectures [input neurons ; hidden neurons ; output neurons], liked [22; 22 ; 2], [22 ; 33 ; 2] and [22 ; 43 ; 2]. Testing with 2 training data sharing and test data, namely comparison 90:10 and 80:20. The Parameters values were used namely learning rate 0.1, 0.3, 0.5, 0.7 and 0.9. The number of epoch was used, that is 15 epoch, 25 epoch and 35 epoch. Based on the tests performed, it was obtained an accuracy system on the 90:10 data comparison of 82% and the 80:20 data ratio of 82% as well. Thus, backpropagation method could be applied in detecting suspected lung diseases.
Clustering Application for UKT Determination Using Pillar K-Means Clustering Algorithm and Flask Web Framework Ahmad Luky Ramdani; Hafiz Budi Firmansyah
Indonesian Journal of Artificial Intelligence and Data Mining Vol 1, No 2 (2018): September 2018
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (586.35 KB) | DOI: 10.24014/ijaidm.v1i2.5126

Abstract

Clustering is one of technique in data mining which has purpose to group data into a cluster. At the end, a cluster will have different data compared with others. This paper discussed about the implementation of clustering technique in determining UKT (Uang Kuliah Tinggal) / Tuition Fee in Indonesia. UKT is a tuition fee where its amount is determined by considering students purchasing power. Most of University in Indonesia often use manual technique in order to classify UKT’s group for each student. Using web-based application, this paper proposed a new approach to automatise UKT’s grouping which leads to give an reasonable recommendation in determining the UKT’s group. Pillar K-Means algorithm had been implemented to conduct data clustering. This algorithm used pillar algorithm to initiate centroid value in K-means algorithm. By deploying students data at Institut Teknologi Sumatera Lampung as case study, the result illustrated that Pillar K-Means and silhouette coefficient value might be adopted in determining UKT’s group
Learning Vector Quantization 3 (LVQ3) and Spatial Fuzzy C-Means (SFCM) for Beef and Pork Image Classification Jasril Jasril; Suwanto Sanjaya
Indonesian Journal of Artificial Intelligence and Data Mining Vol 1, No 2 (2018): September 2018
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (819.086 KB) | DOI: 10.24014/ijaidm.v1i2.5024

Abstract

Base on some cases in Indonesia, meat sellers often mix beef and pork. Indonesia is a predominantly Muslim country. Pork is forbidden in Islam. In this research, the classification of beef and pork image was performed. Spatial Fuzzy C-Means is used for image segmentation. GLCM and HSV are used as a feature of segmentation results. LVQ3 is used as a method of classification. LVQ3 parameters tested were the variety of learning rate values and window values. The learning rate values used is 0.0001; 0.01; 0.1; 0.4; 0.7; 0.9 and the window values used is 0.0001; 0.4; 0.7. The training data used is 90% of the total data, and the testing data used is 10%. Maximum epoch used is 1000 iterations. Based on the test results, the highest accuracy was 91.67%.