Claim Missing Document
Check
Articles

Found 8 Documents
Search

Prediksi Harga Terendah Dan Harga Tertinggi Dengan Menggunakan Metode Anfis Untuk Analisa Teknikal Pada Forex Market Moch. Lutfi
JTIM : Jurnal Teknologi Informasi dan Multimedia Vol 1 No 3 (2019): November
Publisher : Puslitbang Sekawan Institute Nusa Tenggara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v1i3.40

Abstract

Forex Market Is a type of currency trading of the country that handles the world currency market within 24 hours agreed, foreign exchange trading has become an alternative for investors to save more trades in general and traders are required to support good technical analysis of good fundamentals so that able to reap huge profits. Technical analysis is an analysis used to estimate prices will fall at the lower price threshold (support) and the upper price threshold (resistance). Fibonacci Retracement is a method often used for technical analysis of rising prices or rising prices. The data used in this study was downloaded from the FBS Forex Market server which consists of open, high, low, close, and volume data. The next step is grouping data as a preprocessing method with the k-means method to normalize the data before the data is processed in the proposed method, the k-means method is a method of grouping data based on the nearest cluster object. One of the advantages of the k-means method is simple, efficient and easy to apply. In this study, artificial neural network and fuzzy inference system (ANFIS) and Fibonacci Retracement methods are used to predict support and resistance levels. Testing is done using training data and test data with different time intervals. This data produces the highest level of testing based on data from 3 January 2015 - December 2017 and 1 month test data for the period January 2018 100% weekly real data ,. While the value of the accuracy of the trial data period 1 to 2 years and 1 month test data for the period January 2018 daily real data, which is 40%. The average value of the experiment using training data and test data with different time intervals was 52.61%.
PENANGANAN DATA MISSING VALUE PADA KUALITAS PRODUKSI JAGUNG DENGAN MENGGUNAKAN METODE K-NN IMPUTATION PADA ALGORITMA C4.5 Moch. Lutfi; Mochamad Hasyim
Jurnal RESISTOR (Rekayasa Sistem Komputer) Vol. 2 No. 2 (2019): Jurnal RESISTOR Edisi Oktober 2019
Publisher : LPPM STMIK STIKOM Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31598/jurnalresistor.v2i2.427

Abstract

Corn is a staple crop for Indonesian people because most of his life is from the agriculture sector. To increase the productivity of corn, another thing to be aware of is looking at the quality of the corn products. Through empirical observation and observation, research explores and extracts data through the concept of data mining so that neglected data becomes useful. Thus determining the quality of corn production is an important task to help the farmers in determining the classification process. Missing value is a problem in maintaining a quality data. Missing value can be caused by several things, one of which is caused by an error at the time of data entry. Missing value will be a problem when the amount of data in large quantities, so it is very influential in the survey results. Therefore on this research proposed K-NN imputation method to handle missing value data. The results showed the accuracy of the C 4.5 algorithm classification process on the corn production dataset that experienced a missing value accuracy value of 92.90%. Whereas if done with special handling using the method K-NN imputation on the handling process missing value best value at k = 5 of 94.50% with this that the proposed method increases significantly.
PREDIKSI HASIL PEMILU LEGISLATIF MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR BERBASIS BACKWARD ELIMINATION Achmad Saiful Rizal; Moch. Lutfi
Jurnal RESISTOR (Rekayasa Sistem Komputer) Vol. 3 No. 1 (2020): Jurnal RESISTOR Edisi April 2020
Publisher : LPPM STMIK STIKOM Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31598/jurnalresistor.v3i1.517

Abstract

Elections in Indonesia from period to period have undergone some changes. Elections legislative candidates not determined voters, but instead became a political elite authority in accordance with the order of the list of legislative candidates and their number sequence. To perform a prediction one of them with data mining. Data mining can be applied in the political sphere for example to predict the results of the legislative election and others. K-nearest neighbor algorithm is one of the data mining algorithm that performs classification based on learning object against which are closest to the object. Election-related research has been done with the k-nearest neighbor algorithm, but accuracy is obtained that method is still too low, so it takes an additional algorithm to improve accuracy. In this study, the proposed method, namely the method of k-nearest neighbor method combined with backward elimination as a selection of features. The dataset that will be used in the study comes from the KPU Sidoarjo that has special attributes 1 and 13 regular attributes. From the results of the analysis and computation of some methods, it can be concluded that the method of k-nearest neighbor method combined with backward elimination produced some conclusions. First, of the 14 attributes in the dataset, retrieved 8 most influential attribute. Second, the best accuracy are of 96.03% when k = 2 and tested by 10 fold cross validation.
Identifikasi Jenis Penyakit Daun Jagung Menggunakan Deep Learning Pre-Trained Model Muhammad Imron Rosadi; Moch. Lutfi

Publisher : Program Studi Teknik Informatika, Fakultas Teknik, Universitas Yudharta Pasuruan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35891/explorit.v13i2.2690

Abstract

Jagung salah satu kebutuhan pangan utama setelah padi dan terigu di dunia dan termasuk kebutuhan yang penting di Indonesia setelah padi. Identifikasi penyakit pada daun tanaman jagung dapat dilakukan secara manual dengan penglihatan mata manusia berdasarkan warna daun jagung. Namun proses ini membutuhkan waktu yang lama dan kurang akurat sehingga mempengaruhi penambahan biaya perawatan. Untuk mendukung proses identifikasi secara cepat dan akurat dibutuhkan sistem pengolahan citra digital. Pada Penelitian ini mengusulkan metode Convolutional Neural Network (CNN) pre-trained model untuk mendeteksi jenis penyakit pada daun jagung. Deteksi yang dilakukan pada 5 jenis daun jagung yaitu 1 daun sehat dan 4 penyakit daun jagung yaitu karat daun, bercak daun, hawar daun, dan bulai daun. Harapannya metode yang diusulkan mampu mendeteksi penyakit daun jagung secara akurat dan mengurangi waktu komputasi. Berdasarkan hasil ujicoba bahwa transfer learning mampu meningkatkan akurasi dan mengurasi waktu komputasi dengan tingkat akurasi data training 0.85% error rate 0.45% dan data validasi 0.88% error rate 0.54
Implementasi metode K-Nearest Neighbor dan bagging untuk klasifikasi mutu produksi jagung Moch. Lutfi

Publisher : Fakultas Pertanian Universitas Yudharta Pasuruan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (733.766 KB) | DOI: 10.35891/agx.v10i2.1636

Abstract

Corn is an agricultural crop in the Indonesian community, besides rice and soybeans because almost all of the area is fertile with planting seeds, the quality of corn quality that must be fulfilled as a food ingredient is very necessary for crop-producing farmers. The k-nearest neighbor algorithm is a method used to make predictions or classifications of objects based on training data that are the closest to the object or often called the euclidian distance. In this study used replace imputation for the preprocessing stage, missing value and baggin data are used to handle datasets in large scale while k-nearest neighbor is used as a classification of quality of corn quality based on attributes Variatas, Length, Shape, Taste Color, Seasonal Technique, Pest PH. . Based on the test data the best accuracy value is 79.30%, precision is 83.04% while recall with the value of 80.93% is obtained from the results of the performance test of bagging and replace imputation methods on the k-nearest neighbor algorithm with handling of missing value.
Klasifikasi Jenis Tanaman Kelengkeng Berdasarkan Ciri Tekstur Daun Menggunakan Metode Adaptive Neuro Fuzzy Inference System (AFIS) Ahmad Rif’an Firdaus; Moch. Lutfi; Muhammad Faishol Amrulloh

Publisher : Program Studi Teknik Informatika, Fakultas Teknik, Universitas Yudharta Pasuruan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35891/explorit.v14i1.2726

Abstract

Dimocarpus Longan atau kelengkeng merupakan buah yang memiliki beberapa jenis varietas yang dapat dilihat dari tiga ciri yang berbeda yaitu daun, batang dan buah. Namun tidak semua orang dapat mengidentifikasi jenis tanaman kelengkeng dari beberapa ciri tersebut. Salah satunya ciri daun kelengkeng yang susah untuk diidentifikasi jenisnya karena persamaan bentuk yang hampir mirip dengan jenis tanaman kelengkeng lainnya. Salah satu cara untuk mengatasi yang dapat dilakukan untuk membedakan jenis tanaman dengan menggunakan metode citra digital. Oleh karena itu pada penelitian ini menggunakan daun kelengkeng sebagai data citra untuk klasifikasi dan ektraksi fitur untuk identifikasi ciri tanaman kelengkeng. Untuk metode klasifikasi yang digunakan untuk mengklasifikasikan citra daun kelengkeng adalah Adaptive Neuro Fuzzy Sistem (ANFIS) dengan ekstraksi fitur tektur daun tanaman kelengkeng menggunakan metode ekstraksi Gray Level Co-occurance Matrix (GLCM) dan menggunakan citra daun kelengkeng diamond river, new kristal mata lada dan puang rai. Klasifikasi ANFIS merupakan teknik fuzzy inference pada pemodelan berdasarkan pasangan data input dan output. Error yang dilakukan selama pelatihan atau selisih keluaran FIS dengan data training sebesar 0.10475 dengan kemampuan pengenalan atau akurasi sebesar 67.5%.
Pencarian Rute Jasa Pemesanan Penggilingan Padi Berbasis Android Dengan Menggunakan Google Maps Moch Lutfi; Elmaida Khoirotuzzuhria
INFORMAL: Informatics Journal Vol 8 No 1 (2023): Informatics Journal (INFORMAL)
Publisher : Faculty of Computer Science, University of Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19184/isj.v8i1.34772

Abstract

The location where the rice mill service is located is an important thing for most farmers to improve the quality of rice. Clear information about the rice mill is one of the determining factors in choosing a suitable rice mill. For farmers and people who do not know the surrounding area when they are going to do rice milling, it will be difficult to find the nearest rice mill location. There are several weaknesses when using a manual system, including the information obtained is not in accordance with the expected needs, and the distance traveled requires a relatively long time and relatively large cost. The research conducted by the author is to design an application for ordering rice milling services using the waterfall method and using google maps as a method of finding the closest route. The purpose of the study was to determine the application of google maps to the rice mill ordering application. From the results of system testing using blackbox testing, the results show that the application being tested can run and function as expected. While the results of testing the questionnaire by getting an index of 79.75%.
Penanganan Data Tidak Seimbang Menggunakan Hybrid Method Resampling Pada Algoritma Naive Bayes Untuk Software Defect Prediction Moch Lutfi; Arief Tri Arsanto; Muhammad Faishol Amrulloh; Ummi Kulsum
INFORMAL: Informatics Journal Vol 8 No 2 (2023): Informatics Journal (INFORMAL)
Publisher : Faculty of Computer Science, University of Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19184/isj.v8i2.41090

Abstract

Software defect prediction is software data that is used to identify a software module and can also be used to predict software defects. Before carrying out further trials, it is necessary to carry out special handling, especially by using algorithm models as predictions of software defects with the aim of obtaining information from the device being developed. Therefore, it is necessary to predict software defects using appropriate classification and prediction methods, so that the resulting accuracy results are better. In this study, the naïve Bayes algorithm was used as a classification with a resampling technique approach to handle unbalanced data, including SMOTEENN and SMOTETomek. The best accuracy results in the research conducted were 92.5% on the Nasa Repository PC4 dataset