Garuda - Garba Rujukan Digital

Article Per Year (5 Year)

p-Index From 2019 - 2024

7.383

P-Index

This Author published in this journals

All Journal Jurnal Teknologi Informasi dan Ilmu Komputer Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer

Ahmad Afif Supianto

Fakultas Ilmu Komputer, Universitas Brawijaya

Author-ID : 2843367

Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 66 Documents Claim Missing Document

Claim Missing Document

Articles

1 2 3 4 5

Perbandingan Teknik Klasifikasi Dalam Data Mining Untuk Bank Direct Marketing Irvi Oktanisa; Ahmad Afif Supianto
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 5, No 5: Oktober 2018
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Klasifikasi merupakan teknik dalam data mining untuk mengelompokkan data berdasarkan keterikatan data terhadap data sampel. Pada penelitian ini, kami melakukan perbandingan 9 teknik klasifikasi untuk mengklasifikasi respon pelanggan pada dataset Bank Direct Marketing. Perbandingan teknik klasifikasi ini dilakukan untuk mengetahui model dalam teknik klasfikasi yang paling efektif untuk mengklasifikasi target pada dataset Bank Direct Marketing. Teknik klasifikasi yang digunakan yaitu Support Vector Machine, AdaBoost, Naïve Bayes, Constant, KNN, Tree, Random Forest, Stochastic Gradient Descent, dan CN2 Rule. Proses klasifikasi diawali dengan preprocessing data untuk melakukan penghilangan missing value dan pemilihan fitur pada dataset. Pada tahap evaluasi digunakan teknik 10 fold cross validation. Setelah dilakukan pengujian, didapatkan bahwa hasil klasifikasi menunjukkan akurasi terbaik diperoleh oleh model Tree, Constant, Naive Bayes, dan Stochastic Gardient Descent. Kemudian diikuti oleh model Random Forest, K-Nearest Neighbor, CN-2 Rule, AdaBoost dan Support Vector Machine. Dari keempat model yang menunjukkan hasil akurasi terbaik, untuk kasus ini Stochastic Gradient Descent terpilih sebagai model yang memiliki akurasi terbaik dengan nilai akurasi sebesar 0,972 dan hasil visualisasi yang dihasilkan lebih jelas untuk mengklasifikasi target pada dataset Bank Direct Marketing.AbstractClassification is a technique in data mining to classify data based on the attachment of data to the sample data.. In this paper, we present the comparison of 9 classification techniques performed to classify customer response on the dataset of Bank Direct Marketing. The techniques performed to find out the effectiveness model in the classification technique used to classify targets on the dataset of Bank Direct Marketing. The techniques used are Support Vector Machine, AdaBoost, Naïve Bayes, Constant, KNN, Tree, Random Forest, Stochastic Gradient Descent, and CN2 Rule. The classification process begins with preprocessing data to perform missing value omissions and feature selection on the dataset. Cross validation technique, with k value is 10, used in the evaluation stage. After testing, it was found that the classification results showed the best accuracy obtained when using the Tree model, Constant, Naive Bayes and Stochastic Gradient Descent. Afterwards the Random Forest model, K-Nearest Neighbor, CN-2 Rule, AdaBoost, and Support Vector Machine are followed. Of the four models with the high accuracy results, in this case Stochastic Gradient Descent was selected as the best accuracy model with an accuracy value of 0.972 and resulting visualization more clearly to classify targets on the dataset of Bank Direct Marketing.

Rancang Bangun Aplikasi Antrian Poliklinik Berbasis Mobile Rizal Arif Zulfikar; Ahmad Afif Supianto
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 5, No 3: Juni 2018
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Antrian konvensional sudah menjadi polemik yang umum di masyarakat. Lamanya proses dan waktu tunggu antrian sangat mengganggu aktivitas sehari-hari. Pada instansi kesehatan seperti rumah sakit dan poliklinik, dimana pasien juga diharuskan mengantri, dapat berpengaruh pada kondisi pasien. Sistem pendaftaran online yang ada hanya menyediakan pengambilan nomor antrian, namun untuk proses menunggu antrian masih harus datang ke lokasi. Sistem yang ditawarkan memiliki kelebihan pada pilihan variasi jadwal poliklinik, dan pemberian informasi antrian yang sedang berjalan. Pada penelitian ini membahas tentang perancangan dan pengembangan sistem antrian poliklinik yang berbasis pada mobile phone, sehingga pengguna dapat mengakses sistem kapanpun dan dimanapun. Perancangan menggunakna metode MVC untuk memisahkan antara data dan tampilan serta cara pemrosesannya. Pengembangan aplikasi menggunakan hybrid mobile web framework yang dapat digunakan untuk pengembangan multiplatform. Pengujian sitem menggunakan White Box, Black Box, dan Usability Testing telah menunjukkan bahwa struktur dan hasil desain sistem dapat diimplementasikan dengan baik, sehingga sistem dapat berjalan sesuai kebutuhan. AbstractThe conventional queue has become a common polemic in society. The length of processes and waiting time of the queue is very disturbing on daily activities. In health agencies such as hospitals and polyclinics, where patients are also required to queue up, may affect the patient's condition. Existing online registration system only provides queue number retrieval, but for the waiting process, the queue still has to come to the location. The offered system has advantages over the choice of polyclinic schedule variations, and the provision of queue information is running. This research discusses the design and development of a polyclinic queuing system based on a mobile phone so that users can access the system anytime and anywhere. The design uses the MVC method to separate data and display and how to process it. Application development using hybrid mobile web framework that can be used for multiplatform development. System validation method is using White Box, Black Box, and Usability Testing has shown that the structure and results of system design can be implemented well, so the system can run as needed.

Registrasi Citra Dental Menggunakan Feature From Accelerated Segment Test dan Local Gabor Texture For Iterative Point Correspondence Ahmad Afif Supianto; Budi Darma Setiawan
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 4, No 4: Desember 2017
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

AbstrakRegistrasi citra di bidang periodontal telah dikembangkan untuk melakukan evaluasi terhadap tulang alveolar. Masalah yang disebabkan oleh kesalahan saat ekstraksi fitur atau oleh degradasi gambar bisa timbul pada proses pencocokan fitur. Selain itu, teknik registrasi citra yang didasarkan pada fitur seperti titik, identifikasi tepian (edges), kontur, atau fitur yang lain yang biasa digunakan untuk membandingkan gambar dan kemudian memetakannya merupakan teknik yang sangat sensitif terhadap keakuratan pada tahap ekstraksi fitur. Dari kedua argumen ini, maka diperlukan teknik ekstraksi fitur yang tangguh untuk mencegah terjadinya kesalahan pada proses pencocokan fitur sehingga mendapatkan hasil registrasi citra yang akurat. Pada penelitian ini, diusulkan metode baru untuk registrasi citra. Metode yang diusulkan menggunakan metode ekstraksi fitur yang efektif terhadap akurasi dan efisien terhadap waktu komputasi dengan menerapkan Learning Features, yaitu Feature from Accelerated Segment Test (FAST) sebagai metode ekstraksi fitur. Selain itu, akan dilakukan pengembangan terhadap proses pencocokan fitur dengan menerapkan Local Gabor Texture (LGT) pada algoritma Iterative Point Correspondence (IPC) untuk melakukan registrasi pada citra dental periapikal. Uji coba dilakukan terhadap 8 citra grayscale dental periapikal dan berhasil melakukan registrasi citra pada citra dental periapikal dengan nilai akurasi rata-rata diatas 93% dengan jumlah iterasi minimal mulai dari 400 iterasi.Kata kunci: registrasi citra, learning feature, local gabor texture, iterative point correspondence, citra dental periapikalAbstractImage registration in the periodontal field has been developed to evaluate alveolar bones. Problems caused by errors during feature extraction or by image degradation can arise in feature matching process. In addition, image registration techniques that are based on features such as points, identification of edges, contours, or other features commonly used to compare images and map them are very sensitive techniques for accuracy at the feature extraction stage. From both of these arguments, a robust feature extraction technique is needed to prevent mistakes in the feature matching process to get image registration results accurately. In this study, a new method for image registration is proposed. The proposed method uses an effective feature extraction method for accuracy and efficient computing time by applying learning features, which is Feature from Accelerated Segment Test (FAST) as a feature extraction method. In addition, a feature-matching process will be developed by applying Local Gabor Texture (LGT) to the Iterative Point Correspondence (IPC) algorithm to register on the periapical dental images. The experiments were conducted on 8 grayscale dental periapical images and successfully registered the image in periapical dental image with an average accuracy more than 93% with a minimum iteration count starting from 400 iterations.Keywords: image registration, learning feature, local gabor texture, iterative point correspondence, dental periapical images

Implementasi Kombinasi Algoritme Self-Organizing Map dan Fuzzy C-Means untuk Pengelompokan Performa Belajar Siswa pada Media Pembelajaran Digital Nabila Divanadia Luckyana; Ahmad Afif Supianto; Tibyani Tibyani
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 8, No 3: Juni 2021
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2021834402

Media pembelajaran digital mampu menyimpan data dalam bentuk log data yang dapat digunakan untuk melihat perbedaan performa siswa yang tentu saja berbeda-beda antara satu siswa dengan siswa yang lainnya. Perbedaan performa siswa tersebut menyebabkan dibutuhkannya sebuah tahapan yang berfungsi untuk mempermudah proses evaluasi dengan cara menempatkan siswa kedalam kelompok yang sesuai agar dapat membantu tenaga pengajar dalam menangani serta memberikan umpan balik yang tepat pada siswanya. Penelitian ini bertujuan memanfaatkan log data dari sebuah media pembelajaran digital dengan menggunakan kombinasi dari algoritme Self-Organizing Map dan Fuzzy C-Means untuk mengelompokan siswa berdasarkan aktivitas mereka selama belajar dengan media tersebut. Data akan melalui sebuah proses reduksi dimensi dengan menggunakan algoritme SOM, lalu dikelompokkan dengan menggunakan algoritme FCM. Selanjutnya, data dievaluasi dengan menggunakan nilai silhouette coefficient dan dibandingkan dengan algoritme SOM clustering konvensional. Berdasarkan hasil implementasi yang telah dilakukan menggunakan 12 data assignment pada media pembelajaran Monsakun, dihasilkan parameter-parameter optimal seperti ukuran map atau jumlah output neuron sejumlah 25x25 dengan nilai learning rate yang berbeda-beda disetiap assignment. Selain itu, diperoleh pula 2 kelompok siswa pada setiap assignment berdasarkan nilai silhouette coefficient tertinggi yang mencapai lebih dari 0.8 di beberapa assignment. Melalui serangkaian pengujian yang telah dilakukan, penerapan kombinasi algoritme SOM dan FCM secara signifikan menghasilkan cluster yang lebih baik dibandingkan dengan algoritme SOM clustering konvensional. Abstract Digital learning media is able to store data in the form of log data that can be used to see differences in student performance. The difference in student performance causes the need for a stage that functions to simplify the evaluation process by placing students into appropriate groups in order to assist the teaching staff in handling and providing appropriate feedback to students. This study aims to utilize log data from a digital learning media using a combination of the Self-Organizing Map algorithm and Fuzzy C-Means to classify students based on their activities while learning with these media. The data will go through a dimensional reduction process using the SOM algorithm, then grouped using the FCM algorithm. Furthermore, the data were evaluated using the silhouette coefficient value and compared with the conventional SOM clustering algorithm. Based on the results of the implementation that has been carried out using 12 data assignments on the Monsakun learning media, optimal parameters such as map size or the number of neuron outputs are 25x25 with different learning rate values in each assignment. In addition, 2 groups of students were obtained for each assignment based on the highest silhouette coefficient score which reached more than 0.8 in several assignments. Through a series of tests that have been carried out, the implementation of a combination of the SOM and FCM algorithms has significantly better clusters than the conventional SOM clustering algorithm.

Komparasi Metode Data Mining K-Nearest Neighbor Dengan Naive Bayes Untuk Klasifikasi Kualitas Air Bersih (Studi Kasus PDAM Tirta Kencana Kabupaten Jombang) Maulana Aditya Rahman; Nurul Hidayat; Ahmad Afif Supianto
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 12 (2018): Desember 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (538.647 KB)

Water is a chemical compound that is needed for the survival of living things on earth. The widest area on planet earth is water that covers almost 71% of the region on earth. Water is also a very important substance on earth that is needed by all living things from plants, animals and humans. It takes the supervision and processing of the environment around the water source so as to produce clean water quality in accordance with the standard of clean water quality and meet the standard of water that is suitable for human consumption. To determine the classification of clean water quality there are many methods that can be used. To choose the best classification method, it can be comparated between several methods. This study comparing the K-Nearest Neighbor and Naive Bayes methods. Based on several studies, the K-Nearest Neighbor and Naive Bayes methods are quite good and yield a high degree of accuracy. Based on the test result, the average accuracy value of K-Nearest Neighbor method is 82.42% and the average accuracy of Naive Bayes method is 70.32%. It can be concluded that the best method for water quality classification is K-Nearest Neighbor method.

Pemilihan Alternatif Tanaman Obat Terhadap Penyakit Hipertensi Menggunakan Metode Analytical Network Process (ANP) dan Simple Multi Attribute Rating Technique (SMART) Linda Pratiwi; Indriati Indriati; Ahmad Afif Supianto
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 12 (2018): Desember 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (711.595 KB)

Medicinal plants contain active substances aims for healing and preventing of various types of diseases. Various types of medicinal plants each has certain criteria which result in difficulty in determining the alternative medicinal plants as the best priority. This research aims to select alternative medicinal plants which have nutritious substances for hypertension disease treatment. Not only nutritious substances, but also considering the price, availability and taste of the plant. Hypertension is a disease caused by high blood pressure. The selection of alternative medicinal plants for hypertension disease using Analytical Network Process (ANP) and Simple Multi Attribute Rating Technique (SMART) method. Analytical Network Process (ANP) method is used for determining the weights of each of the supporting criteria and Simple Multi Attribute Rating Technique (SMART) method is used for ranking of alternative medicinal plants selection. This research uses 10 data of medicinal plants to be tested. The result of Analytical Network Process (ANP) and Simple Multi Attribute Rating Technique (SMART) method use Spearman Rank correlation test with rs = 0.964 that means a relationship system and expert approach perfectly.

Identifikasi Penyakit Mata Menggunakan Metode Learning Vector Quantization (LVQ) Entra Betlin Ladauw; Dian Eka Ratnawati; Ahmad Afif Supianto
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 12 (2018): Desember 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (427.131 KB)

Taking care and maintaining healthy eyes are very important for human, because eyes are one of the senses that help human to do daily activities. Eyes that give visual information to human, cannot be separated from the threat of many eyes diseases. The diseases can attack from small to big scale. Unfortunately, eyes diseases are usually considered not to have such potential to harm human, so eyes health often to be ignored by people in general. Therefore, in this paper a system to identify eyes diseases has been developed using Learning Vector Quantization (LVQ) method. This method can give classification to a pattern that represent specific class, which will move to a nearer position to corresponding class when the classification data point is true. In this research, there are 21 symptoms and 9 eyes diseases that processed in training and testing processes, where the data were divided into training data and testing data. In training process, LVQ method did some stages to get final weight. The weight will be used in testing process. Using LVQ method, obtained parameter values are Î± = 0.4, Dec Î± = 0.8, Min Î± = 0.00001, Max Epoch = 25, training data = 100 data (80%) and data test = 25 data (20%). From accuracy testing for this system, the result show 82.80% average accuracy and 92% highest accuracy, that means this system works fine. So, it can be concluded that LVQ method can be used for eyes diseases identification.

Peramalan Debit Bendungan Dengan Menggunakan Metode Backpropagation dan Algoritme Genetika Beta Deniarrahman Hakim; Indriati Indriati; Ahmad Afif Supianto
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 1 (2019): Januari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (521.985 KB)

Dam discharge forecasting is needed to plan water allocation plans for various needs such as for Hydropower plant, flood control and irrigation. Artificial neural network in this case backpropagation method has a learning method to change the weight of the value of the architecture of the artificial neural network.#Genetic algorithms can optimize the#weight of artificial neural networks to avoid the occurrence of a minimum local which is a weakness of backpropagation. Genetic algorithms will optimize the weight#of the artificial neural network so individuals which are produced as a weight representation with the best fitness value resulting from the optimization process with the genetic algorithm then used as the initial weight of the artificial neural network backpropagation method. The data used as input data is the dam discharge time series data the previous months. The data used is monthly debit data from 2008 to 2017. Input data will be processed to produce an output value which is the forecasted value of the dam discharge in the next month. The optimal training parameters for genetic algorithm and backpropagation training are the population size=100, the generation=100, Cr and Mr combination 0,6 and 0,4, the number of iterations=500, the value of learning rate=0,7. The test results using optimal parameters get the MSE value=0,04188

Query Expansion Pada LINE TODAY Dengan Algoritme Extended Rocchio Relevance Feedback Chandra Ayu Anindya Putri; Indriati Indriati; Ahmad Afif Supianto
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 1 (2019): Januari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (387.742 KB)

LINE TODAY provides access to up-to-date news contents. Data on LINE TODAY are used to be able to do search engine feature. Query Expansion technique will be very useful if it is to be combined with search engine system where the queries inputted by users are combined with additional queries from the system. These additional queries will make queries generated by users more specific. In addition, users feedback (user judgement/explicit relevance feedback) assessing on each news can minimize ambiguous queries. The process begins with preprocessing technique consisting of several stages which are cleansing, case folding, tokenization, filtering, and stemming. And then, term weighting and cosine similarity. The next process is calculated using the Extended Rocchio Relevance Feedback method which is a traditional method from Rocchio Relevance Feedback to generate an additional queries. The results are obtained from implementation and testing process of Query Expansion on LINE TODAY with Extended Rocchio Relevance Feedback Algorithm resulted an average Precision value of 0.53308, Recall value of 0.81708, F-Measure value of 0.59553, and Accuracy value of 0.9574. The accuracy value obtained with Extended Rocchio Relevance Feedback method based on user judgement increase by 2% compared to automated search by the method of Rocchio Relevance Feedback.

Implementasi Metode Backpropagation Untuk Peramalan Luas Area Terbakar di Hutan dengan Inisialisasi Bobot Nguyen-Widrow Afrizal Aminulloh; Sigit Adinugroho; Ahmad Afif Supianto
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 1 (2019): Januari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (346.969 KB)

Forest fires are a serious event that must be watched out for areas dominated by forest areas. In forest fires, there are several factors that can affect the occurrence of fires such temperature, humidity, rain, wind, and others. This paper implements the backpropagation method to predict the area of the fire. The input used is a factor that influences the occurrence of 7 forest fires. The process of backpropagation method begins with normalizing input data with a range based on the activation function used, after that initialization is weighted and can use the Nguyen-Widrow algorithm, feeds the feedforward and continues to the next process, feedbackward with the MSE requirement less than the error or iteration limit. less than the same as the maximum iteration, if the requirements have been met the output will be normalized, will get a forecasting value, and the last process calculates the results of MSE and SMAPE as a result of the success of the forecasting process. Based on the results of the tests that have been done, it is obtained that the optimal parameters are 5 hidden layer neurons, 0.1 learning rate, and maximum 1500 iterations. The highest average SMAPE result from this study is 49,1796 and the lowest SMAPE average is 31,4492 which shows that the backpropagation method can be used to forecast burn areas in the forest.

Co-Authors Abdul Harris Wicaksono Achmad Firmansyah Sulaeman Adhitya Pratama Wijayakusuma Adinugroho, Sigit Admaja Dwi Herlambang Afrizal Aminulloh Aldous Elpizochari Ammar Burhanuddin Sayuti Anam, Syaiful Andi Reza` Perdanakusuma Anggie Tamara Blanzesky Annisa Salamah Rahmadhani Bayu Rahayudi Beta Deniarrahman Hakim Bilal Benefit Budi Darma Setiawan Candra Dewi Carlista Naba Chandra Ayu Anindya Putri Dian Eka Ratnawati Dito William Hamonangan Gultom Dityo Kukuh Utomo Diva Devina Djoko Pramono Djoko Pramono Entra Betlin Ladauw Fadhyl Farhan Alghifari Fawwaz Roja Mahardika Febrian Pandu Widhianto Feri Setyo Efendi Fitra Abdurrachman Bachtiar Galih Wisnu Murti Gede Jaya Widhi Aryadi Hafizh Yuwan Fauzan Haryo Setowibowo Hilmi Rezkian Aziz Dama Ignatius Chandra Christian Imaning Dyah Larasati Indriati Indriati Iqbal Setya Nurfimansyah Irvi Oktanisa Izza Isma Komang Candra Brata Linda Pratiwi Lutfi Fanani Lutfi Putra Gusrinda Mardiani Putri Agustini Maulana Aditya Rahman Mochamad Bachtiyar Eko Cahyo Putro Mochammad Izzuddin Mohammad Birky Auliya Akbar Mohammad Malik Abdul Azis Muhammad Aminul Akbar Muhammad Hasan Johan Alfarizi Muhammad Tanzil Furqon Nabila Divanadia Luckyana Nanang Yudi Setiawan Nanda Samsu Dhuha Ni Wayan Surya Wardhani Niken Hendrakusma Wardani Novira Azpiranda Nur Aenun Marjan Nur Laita Rizki Amalia Nur Sa'diyah Nur Shafiya Nabilah Salam Nurul Hidayat Onky Prasetyo Puras Handharmahua Rafid Agung Pradana Retno Indah Rokhmawati Rifaldi Raya Rifky Yunus Krisnabayu Riska Agustia Risqi Auliatin Nisyah Rizal Arif Zulfikar Rizka Awaliyah Nurul Putri Rosa Nur Madinah Rudi Gunawan Ryan Dwi Pambudi Santi Yunika Sufiana Satrio Agung Wicaksono Satrio Hadi Wijoyo Sri Wulan Utami Vitandy Tibyani Tibyani Tri Berlian Novi Vito Ramadhan Welly Purnomo Widhy Hayuhardhika Nugraha Putra Willy Aditya Nugraha Yusi Tyroni Mursityo Yustinus Radityo Pradana

Title

Found 66 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 66 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 66 Documents
Search