Article Per Year (5 Year)
p-Index From 2019 - 2024
1.554
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering Techno.Com: Jurnal Teknologi Informasi Bulletin of Electrical Engineering and Informatics Jurnal Teknologi Informasi dan Ilmu Komputer Faktor Exacta Jurnal Telematika Jurnal Riset Informatika Sains, Aplikasi, Komputasi dan Teknologi Informasi
Devi Fitrianah
Universitas Mercu Buana
Aerospace Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 9 Documents
Search

 1 
Implementation of deep neural networks (DNN) with batch normalization for batik pattern recognition Ida Nurhaida; Vina Ayumi; Devi Fitrianah; Remmy A. M. Zen; Handrie Noprisson; Hong Wei
International Journal of Electrical and Computer Engineering (IJECE) Vol 10, No 2: April 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (580.261 KB) | DOI: 10.11591/ijece.v10i2.pp2045-2053

Abstract

One of the most famous cultural heritages in Indonesia is batik. Batik is a specially made drawing cloth by writing Malam (wax) on the cloth, then processed in a certain way. The diversity of motifs both in Indonesia and the allied countries raises new research topics in the field of information technology, both for conservation, storage, publication and the creation of new batik motifs. In computer science research area, studies about Batik pattern have been done by researchers and some algorithms have been successfully applied in Batik pattern recognition. This study was focused on Batik motif recognition using texture fusion feature which is Gabor, Log-Gabor, and GLCM; and using PCA feature reduction to improve the classification accuracy and reduce the computational time. To improve the accuracy, we proposed a Deep Neural Network model to recognise batik pattern and used batch normalisation as a regularises to generalise the model and to reduce time complexity. From the experiments, the feature extraction, selection, and reduction gave better accuracy than the raw dataset. The feature selection and reduction also reduce time complexity. The DNN+BN significantly improve the accuracy of the classification model from 65.36% to 83.15%. BN as a regularization has successfully made the model more general, hence improve the accuracy of the model. The parameters tuning also improved accuracy from 83.15% to 85.57%.
Studi Komparasi Algoritma Klasifikasi C5.0, SVM dan Naive Bayes dengan Studi Kasus Prediksi Banjir Devi Fitrianah; Wawan Gunawan; Anggi Puspita Sari
Techno.Com Vol 21, No 1 (2022): Februari 2022
Publisher : LPPM Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33633/tc.v21i1.5348

Abstract

Indonesia merupakan negara troips yang memiliki jumlah penduduk yang banyak sehingga mengakibatkan banyak sekali bencana alam yang harus diterima oleh Indonesia. Penelitian ini difokuskan pada bencana banjir yang nantinya dapat dimanfaatkan untuk mengatasi bencana kekeringan dengan cara penampungan air hujan. Selanjutnya berdasarkan luas wilayah dan jumlah penduduk yang ada, jika kita bandingkan dengan bencana banjir yang terjadi maka provinsi Jawa Barat yang seharusnya dapat perhatian lebih besar karena luas wilayah untuk masing-masing penduduk paling kecil jika dibandingkan dengan provinsi yang lain. Penelitian ini yang dilakukan menggunakan algoritma SVM, C5.0 dan Naive Bayes yang digunakan untuk melakukan prediksi banjir untuk membantu pencegahan kebencanaan agar tidak tejadi korban yang lebih banyak. algoritma SVM dan C5.0 memiliki nilai akurasi yang sama yaitu sebesar 93.75% sedangkan algoritma Naive Bayes memiliki nilai akurasi sebesar 81,25. Sehingga dapat disimpulkan bahwa algoritma ini lebih akurat dan efisien untuk digunakan untuk melakukan prediksi. Sedangkan untuk waktu pemrosesannya maka algoritma Naive Bayes bisa dikatakan lebih cepat jika dibandingkan algoritma SVM dan juga algoritma C5.0.
Extractive text summarization for scientific journal articles using long short-term memory and gated recurrent units Devi Fitrianah; Raihan Nugroho Jauhari
Bulletin of Electrical Engineering and Informatics Vol 11, No 1: February 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v11i1.3278

Abstract

Along with the increasing number of scientific publications, many scientific communities must read the entire text to get the essence of information from a journal article. This will be quite inconvenient if the scientific journal article is quite long and there are more than one journals. Motivated by this problem, encourages the need for a method of text summarization that can automatically, concisely, and accurately summarize a scientific article document. The purpose of this research is to create an extractive text summarization by doing feature engineering to extract the semantic information from the original text. Comparing the long short-term memory algorithm and gated recurrent units and were used to get the most relevant sentences to be served as a summary. The results showed that both algorithms yielded relatively similar accuracy results, with gated recurrent units at 98.40% and long short-term memory at 98.68%. The evaluation method with matrix recall-oriented understudy for gisting evaluation (ROUGE) is used to evaluate the summary results. The summary results produced by the LSTM model compared to the summary results using the latent semantic analysis (LSA) method were then obtained recall values at ROUGE-1, ROUGE-2, and ROUGE-L respectively were 76.25%, 59.49%, and 72.72%.
Analisis Rekomendasi Calon Debitur Motor pada PT.XYZ menggunakan Algortima C 4.5 Lilis Nurellisa; Devi Fitrianah
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 7, No 4: Agustus 2020
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2020742080

Abstract

PT.XYZ merupakan perusahaan jasa pembiayaan atau leasing dengan berkonsentrasi kepada pembiayaan sepeda motor. Dalam bisnisnya PT.XYZ sering sekali dihadapkan oleh masalah kredit macet atau bahkan penipuan. Hal ini dikarenakan kesalahan dalam pemberian kredit kepada calon debitur yang tidak potensial. Jika tidak ditangani hal ini tentu saja akan berdampak buruk bagi perusahaan. Perusahaan mengalami penurunan kemampuan dalam membayar angsuran pinjaman ke perbankan bahkan dapat berdampak pada kebangkrutan. Dalam hal ini PT.XYZ perlu melalukan analisis untuk menentukan calon debitur yang potensial dengan menggunakan data driven method atau pendekatan berbasis kepada data. Yaitu pengambilan keputusan dengan melihat data pengajuan kredit yang pernah ada sebelumnya yang disebut juga sebagai supervised learning. Algoritma yang digunakan adalah algoritma C4.5 karena algoritma ini dapat mengklasifikasi data yang sudah ada sebelumnya. Dengan algoritma ini akan dihasilkan sebuah pohon keputusan yang akan membantu PT.XYZ dalam pengambilan keputusan. Dengan pengujian menggunakan 3587 sampel data pengajuan kredit dalam kurun waktu 1 tahun akurasi yang didapatkan ialah 97,96%. Dengan begitu hal ini menunjukkan bahwa metode klasifikasi menggunakan algoritma C4.4 berhasil diimplementasikan dengan baik. Hal ini diharapkan dapat membantu PT.XYZ dalam merekomendasikan calon debitur yang potensial. AbstractPT. XYZ is a finance or leasing service company by concentrating on motorcycle financing. In its business, PT. XYZ is often faced with problems of bad credit or even fraud. This is due to an error in giving credit to potential debtors. If it is not handled this, of course, will have a bad impact on the company. Companies experiencing a decline in the ability to repay loan installments to banks can even have an impact on bankruptcy. In this case, PT. XYZ needs to do an analysis to determine potential debtors using data-driven methods or data-based approaches. That is decision making by looking at credit application data that has never been before, which is also called supervised learning. The algorithm used is the C4.5 algorithm because this algorithm can classify pre-existing data. With this algorithm, a decision tree will be produced that will help PT. XYZ in decision making. By testing using 3587 samples of credit filing data within a period of 1 year the accuracy obtained was 97.96%. That way this shows that the classification method using the C4.4 algorithm is successfully implemented properly. This is expected to help PT. XYZ in recommending potential debtors.
Penerapan Metode Machine Learning untuk Prediksi Nasabah Potensial menggunakan Algoritma Klasifikasi Naïve Bayes Devi Fitrianah; Saruni Dwiasnati; Hanny Hikmayanti H; Kiki Ahmad Baihaqi
Faktor Exacta Vol 14, No 2 (2021)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v14i2.9297

Abstract

Customers are people who trust the management of their money in a bank or other financial service party to be used in banking business operations, thereby expecting a return in the form of money for their savings. To reach information to increase company profits, a method is needed to be able to provide knowledge in supporting the data that the company has. The model can be obtained by using predictive data processing of customer data that is categorized as potential or not potential. Data processing can be done using Machine Learning, namely classification techniques. This technique will produce a churn prediction model for determining the category of customers who fall into the Potential or Not Potential category and find out what accuracy value will be generated by applying the classification technique using the Naïve Bayes Algorithm. The parameters used in this study are Gender, Age, Marital Status, Dependent, Occupation, Region, Information. The data used are 150 data from customers who have participated in the savings program to find out whether the customer is in the Potential or Non-Potential category. The accuracy results generated using this data are 86.17% of the tools used by Rapidminner.
Penerapan Fuzzy Sugeno Orde Satu dalam Prediksi Pembelian Devi Fitrianah; Wawan Gunawan; Anggi Puspita Sari
Faktor Exacta Vol 14, No 4 (2021)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v14i4.11268

Abstract

Given the rapid advancement of information technology has a great influence in the fields of industry and services. This brings changes in competition between companies, so that company players must always create various techniques to survive. This study aims to assist SMEs in making purchases of the products they sell so that there is no excess stock. This research is calculated using the Fuzzy Sugeno algorithm with a system inference method that can be applied to determine the prediction of the number of purchases of goods. The prediction generated for the test data at week 30 is 60 pcs and this is less when compared to the real data, namely 70 pcs so that it can avoid overstock. Furthermore, the prediction results from the test data at week 21 to week 30 are tested to determine the error rate using the MAPE method, so that the result is 31.67%, and that means that the test is considered reasonable (reasonable).
Penerapan Metode Regresi Linear Untuk Prediksi Penjualan Properti pada PT XYZ Ghebyla Najla Ayuni; Devi Fitrianah
Jurnal Telematika Vol 14, No 2 (2019)
Publisher : Institut Teknologi Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The purpose of this research is to obtain property sales predictions based on property sales data at PT XYZ. Linear regression is used as a prediction method with the quantity or number of properties sold as an effect variable and the period of property sale as a causal variable. Accuracy testing of prediction results is carried out using MSE, RMSE, and MAPE. Based on the results of research conducted using property sales data for a period of five years, it was found that the number of sales in the following month is predicted to be sold as many as 4 units for property rumah 59, 2 units of rumah sudut, 6 types consisting of rumah 28, rumah 39, rumah 62, rumah 73, rumah 84, and rumah 115 each as many as 1 unit, and the remaining 5 types namely kavling, ruko, rumah 58, rumah 67, and rumah 72 are predicted to not experience any sales. The results of testing the accuracy of all types display the value of MSE, RMSE, and MAPE that are meet with the standards. Based on this results, it can be said that the prediction of property sales using linear regression method is categorized as very good.Tujuan dari penelitian ini adalah untuk mendapatkan prediksi penjualan properti berdasarkan data penjualan properti pada PT XYZ. Regresi linear digunakan sebagai metode prediksi dengan kuantiti atau jumlah properti yang terjual sebagai variabel akibat dan periode penjualan properti sebagai variabel penyebab. Pengujian keakurasian terhadap hasil prediksi dilakukan menggunakan MSE, RMSE, dan MAPE. Berdasarkan hasil penelitian yang dilakukan dengan menggunakan data penjualan properti selama kurun waktu lima tahun, didapatkan bahwa jumlah penjualan pada bulan berikutnya untuk properti tipe rumah 59 diprediksi akan terjual sebanyak 4 unit, tipe rumah sudut sebanyak 2 unit, 6 tipe yang terdiri atas rumah 28, rumah 39, rumah 62, rumah 73, rumah 84, dan rumah 115 masing-masing sebanyak 1 unit, dan 5 tipe sisanya yaitu kavling, ruko, rumah 58, rumah 67, dan rumah 72 diprediksi tidak akan mengalami penjualan. Prediksi penjualan properti menggunakan metode regresi linear ini dapat dikatakan tergolong dalam kategori sangat baik didasari hasil pengujian keakurasian terhadap keseluruhan tipe yang menampilkan nilai MSE, RMSE, dan MAPE yang memenuhi standar.
Analisa Perbandingan Algoritma CNN Dan MLP Dalam Mendeteksi Penyakit COVID-19 Pada Citra X-Ray Paru Novelinda Permata Wulandari; Devi Fitrianah
Sains, Aplikasi, Komputasi dan Teknologi Informasi Vol 3, No 2 (2021): Sains, Aplikasi, Komputasi dan Teknologi Informasi
Publisher : Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/jsakti.v3i2.5129

Abstract

Pada bulan Maret 2020 Organisasi Kesehatan Dunia atau WHO (World Health Organization) menyatakan bahwa COVID-19  sebagai pandemi global. Untuk mengendalikan penyebaran COVID-19 ini dibutuhkan diagnosis secara dini dan akurat. Saat ini, standar emas dalam diagnosis COVID-19 didasarkan pada Reverse Transcripttion Polymerase Chain Reaction (RT-PCR) yakni mengambil dari sample pasien secara langsung. Dalam menangani masalah yang ada dibutuhkan metode diagnostic alternative, seperti melakukan pengolahan dan analisis dari pencitraan medis. Tujuan dari penelitian ini adalah untuk melakukan diagnosis alternatif menggunakan data citra paru untuk dapat mengklasifikasi mana paru yang terkena COVID-19 dan mana paru yang sehat. Metode yang digunakan dalam mengklasifikasi data citra adalah dengan pendekatan Deep Learning. Pada kasus ini, penelitian ini akan melakukan perbandingan algoritma CNN dan MLP untuk dapat melihat mana dari keduanya yang menghasilkan hasil yang lebih baik. Hasil yang didapat menunjukkan bahwa CNN lebih unggul dengan akurasi sebesar 97,14% dibandingkan dengan MLP dengan akurasi sebesar 91,39%. Hal ini dikarena Algoritma CNN memiliki lebih banyak lapisan dibandingkan dengan MLP, serta Algoritma CNN dapat bekerja dengan baik pada data spasial.
COMPARATIVE STUDY OF FUZZY C-MEANS AND K-MEANS ALGORITHM FOR GROUPING CUSTOMER POTENTIAL IN BRAND LIMBACK Difa Lazuardi Aditya; Devi Fitrianah
Jurnal Riset Informatika Vol. 3 No. 4 (2021): September 2021 Edition
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34288/jri.v3i4.98

Abstract

The customer is a stakeholder for a business, to maintain and increase customer enthusiasm and develop it for the company's performance, it is necessary to do customer segmentation which aims to find out potential customers. This study uses purchase transaction data from Brand Limback customers in the period 2020. The use of RFM (Recency, Frecuency, Monetary) analysis helps in determining the attributes used for customer segmentation. To determine the optimal number of clusters from the RFM dataset, the Elbow method is applied. The datasets generated from RFM are grouped using the Fuzzy C-Means and K-Means algorithms, the two algorithms will compare the quality in the formation of clusters using the Silhoutte Coefficient and Davies-Bouldin Index methods. Customer segmentation from the RFM dataset that has been clustered produces 7 optimal clusters, namely Cluster 0 is a bronze customer. Cluster 1 is a silver customer. Cluster 2 is a gold customer. Cluster 3 is a platinum customer. Cluster 4 is a diamond customer. Cluster 5 is a super customer, and cluster 6 is a superstar customer. The cluster validation of k-means using the silhouette coefficient produces a value of 0.934 while the Davies bouldin index produces a value of 0.155 and the validation results of the fuzzy c-means algorithm using the silhouette coefficient produces a value of 0.921 while the Davies bouldin index produces a value of 0.145.
Co-Authors Anggi Puspitasari, Anggi Ayumi, Vina Baihaqi, Kiki Ahmad Difa Lazuardi Aditya Ghebyla Najla Ayuni Hanny Hikmayanti H Hong Wei Ida Nurhaida Lilis Nurellisa Noprisson, Handrie Novelinda Permata Wulandari Raihan Nugroho Jauhari Remmy A. M. Zen Saruni Dwiasnati Wawan Gunawan