Article Per Year (5 Year)
p-Index From 2020 - 2025
2.062
P-Index
This Author published in this journals
All Journal JURNAL MEDIA INFORMATIKA BUDIDARMA Jurnal RESISTOR (Rekayasa Sistem Komputer) Journal of Information System, Applied, Management, Accounting and Research Building of Informatics, Technology and Science Technologia: Jurnal Ilmiah JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Abdi Kami : Jurnal Pengabdian Kepada Masyarakat Jurnal Pendidikan dan Teknologi Indonesia Jurnal Media Informatika Jurnal Algoritma Jurnal Informatika dan Teknologi Informasi Internet of Things and Artificial Intelligence Journal Innovative: Journal Of Social Science Research
Awal, Elsa Elvira
Unknown Affiliation
Religion Agriculture, Biological Sciences & Forestry Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Public Health Other

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search

 1   2 
Studi Komparasi Metode Machine Learning untuk Klasifikasi Citra Huruf Vokal Hiragana Amrustian, Muhammad Afrizal; Muliati, Vika Febri; Awal, Elsa Elvira
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 5, No 3 (2021): Juli 2021
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v5i3.3083

Abstract

Japanese is one of the most difficult languages to understand and read. Japanese writing that does not use the alphabet is the reason for the difficulty of the Japanese language to read. There are three types of Japanese, namely kanji, katakana, and hiragana. Hiragana letters are the most commonly used type of writing. In addition, hiragana has a cursive nature, so each person's writing will be different. Machine learning methods can be used to read Japanese letters by recognizing the image of the letters. The Japanese letters that are used in this study are hiragana vowels. This study focuses on conducting a comparative study of machine learning methods for the image classification of Japanese letters. The machine learning methods that were successfully compared are Naïve Bayes, Support Vector Machine, Decision Tree, Random Forest, and K-Nearest Neighbor. The results of the comparative study show that the K-Nearest Neighbor method is the best method for image classification of hiragana vowels. K-Nearest Neighbor gets an accuracy of 89.4% with a low error rate.
Analisis Kinerja Algoritma Decision Tree Dan Random Forest Dalam Klasifikasi Penyakit Kardiovaskular Utami, Nisa; Baihaqi, Kiki Ahmad; Awal, Elsa Elvira; Waiddin, Deden
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5722

Abstract

Cardiovascular disease is a disease with a fairly high number of deaths. In Indonesia, the term cardiovascular is more popular with heart disease, which is a condition that can cause narrowing and blockage of blood vessels. Cardiovascular disease has two risks, the first is a risk that can be changed, such as stress, increased blood pressure, unhealthy diet, increased glucose levels, abnormal cholesterol and lack of physical activity. Meanwhile, risks that cannot be changed include family disease, gender, age and obesity. In this research, we can examine and analyze the performance of the two best classification algorithms, namely the decision tree algorithm and the random forest algorithm, in classifying cardiovascular disease based on the cause of the disease. The aspects studied are the performance results of each algorithm and evaluated using Area Under the Curve (AUC), classification report, k-Fold Cross Validation and Confusion matrix. The dataset used was taken from the Kaggle website with the data used being Cardiovascular Disease data which consists of 68.205 rows (patient data) and 17 attributes. . Based on the evaluation results using the Area Under The Curve (AUC) value, the highest result was obtained at 0.761 by the Random Forest algorithm with balanced data conditions with Random oversampling. Meanwhile, the lowest AUC value was obtained by the Decision Tree algorithm with unbalanced data of 0.592. Based on these results, it is known that the Random Forest algorithm with a balanced data scheme is a better algorithm, with a balanced data scenario using SMOTE and Random Oversampling techniques.
Model Prediksi Perubahan Tutupan Lahan Pada Area Kebakaran Lahan Gambut Menggunakan Model Cellular Automata Markov Awal, Elsa Elvira; Sukaesih Sitanggang, Imas; Syaufina, Lailan
Jurnal Informatika dan Teknologi Informasi Vol. 1 No. 3: Januari 2023
Publisher : PT. Bangun Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56854/jt.v1i3.141

Abstract

During 2016 Riau Province experienced 10,676 hectares of forest and land fires on fire, where Rokan Hilir District was the largest area of forest fires that reach 3,416 hectares. The area of peatlands in Indonesia is currently experiencing degradation because of peatland fires that, result land-use, land-use changes, and forestry. The purpose of this study was to create a prediction model of land cover change in land fire areas using the Cellular Automata Markov model. The Markov Cellular Automata model is used to predict changes in land cover because this model is very suitable to be applied in high-detail spatial phenomena. The results of this study indicate that in the 2000-2003 period is used to predict land cover changes in 2006 due to forest the land fire in March 2002. The results show that plantations has the most significant change, namely 25.36% with a Kappa value of 95.74%. The prediction model of the period 2006-2009 is used to predict land cover changes in 2012 due to forest the land fire in July 2007. The results show that swamp shrub experienced a change of 74.94% with a Kappa value of 93.22%. The prediction model of the period 2014-2016 is used to predict land cover changes in 2018 due to forest the land fire in June 2015. The results show that swamp bushland cover class experienced the most significant reform of 55.07% with a Kappa value of 68.59%. The prediction results from the three periods show good and acceptable results, however the area of land cover as the result of prediction model has quite large difference with the actual land cover. Keywords: cellular automata markov, land fires, peatlands, land-use land-use changes and forestry
SOSIALISASI APLIKASI UNTUK MELAKUKAN DETEKSI DINI KECANDUAN PERMAINAN ONLINE PADA SISWA SMK N 1 KLARI KARAWANG Masruriyah, Anis Fitri Nur; Wahiddin, Deden; Novita, Hilda Yulia; Awal, Elsa Elvira
ABDI KAMI: Jurnal Pengabdian Kepada Masyarakat Vol 5 No 2 (2022): (Oktober 2022)
Publisher : LPPM Institut Agama Islam (IAI) Ibrahimy Genteng Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69552/abdi_kami.v5i2.1470

Abstract

The global COVID-19 pandemic has an impact on people's activities in the world, including in Indonesia. The policies of each country to overcome this condition also vary, one of which is the Indonesian government which imposes limited face-to-face activities offline. Many activities must be carried out online to minimize the transmission of COVID-19. Finally, this has an impact on many people who spend time with their gadgets to play permainans with cellphones, laptops or other electronic media. Playing permainans has benefits for relaxation from the fatigue of online activities, but if this continues it will result in permainan addiction. So that community service activities for the socialization of permainan addiction detection applications are carried out, so that users are able to control the use of devices when playing permainans. So, if an addiction is detected, you can ask experts for help, for school children you can have an initial consultation with a Counseling Guidance teacher.
Perbandingan Algoritma Apriori dan Algoritma FP-Growth dalam Menentukan Pola Penjualan Pupuk Rachmawati, Dhea; Cahyana, Yana; Awal, Elsa Elvira; Faisal, Sutan
Jurnal RESISTOR (Rekayasa Sistem Komputer) Vol. 7 No. 1 (2024): Jurnal RESISTOR Edisi April 2024
Publisher : Prahasta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31598/jurnalresistor.v7i1.1527

Abstract

Sistem informasi sangatlah penting pada era ini, dengan mengetahui data kita dapat membuat strategi pada suatu bisnis. contohnya kebutuhan pupuk di setiap daerah tentunya berbeda-beda, kita sebagai distributor bisnis pupuk harus mengetahui produk penjualan tertinggi hingga terendah pada setiap daerah. Oleh karena itu dengan memanfaatkan metode data mining yaitu teknik penggalian informasi baru dari kumpulan data yang bertujuan untuk mengetahui pola pembelian konsumen dengan meningkatkan penjualan produk, perusahaan penjualan perlu memikirkan berbagai strategi untuk mencapai hal tersebut dengan menggunakan perbandingan algoritma apriori dan algoritma fp-growth dalam data penjualan pupuk pada tahun 2022 di PT. Pupuk Kujang. Hasil penelitian ini, pada kedua algoritma menghasilkan Support dengan nilai tertinggi 59% dan Confidence dengan nilai tertinggi 100%, namun dari hasil aturan asosiasi algoritma apriori menghasilkan 136 aturan dan algoritma fp-growth menghasilkan 156 aturan. Dengan demikian, algoritma fp-growth dapat dikatakan mempunyai kinerja yang lebih baik dalam menghasilkan aturan asosiasi jika dibandingkan dengan Algoritma Apriori. Dalam penelitian ini juga memanfaatkan Association Rules seperti Cross-Selling dan Up-Selling. Pada asosiasi ini, bisnis dapat menerapkan strategi penjualan silang yang efektif, menawarkan produk tambahan atau peningkatan yang relevan kepada pelanggan, sehingga dapat meningkatkan pendapatan pada penjualan pupuk di PT. Pupuk Kujang. Kata kunci: Bisnis, Association Rule, Algoritma Apriori, Algoritma Fp-Growth.
Klasterisasi Tingkat Kemiskinan Kabupaten/Kota di Indonesia Menggunakan Algoritma K-Means dan K-Medoids Pratiwi, Gita Risky; Wahiddin, Deden; Awal, Elsa Elvira; Fauzi, Ahmad
Jurnal Algoritma Vol 21 No 2 (2024): Jurnal Algoritma
Publisher : Institut Teknologi Garut

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

Abstract

Kemiskinan adalah ketika sebuah masyarakat memiliki akses fisik yang terbatas terhadap lingkungan dasar. Kondisi permukiman miskin ini seringkali jauh di bawah standar kelayakan dan menyebabkan orang-orang di sana kesulitan mendapatkan uang untuk hidup. Fokus penelitian ini adalah untuk menentukan tingkat kemiskinan di Kab/Kota di Indonesia. Karena ada peningkatan angka kemiskinan di Indonesia, clustering diperlukan untuk pemerintah dapat memberikan bantuan yang tepat kepada mereka yang paling membutuhkan. Metode yang digunakan adalah algoritma K-Means dan K-Medoids. Hasil dari pengelompokkan ini menghasilkan cluster 0 menunjukkan tingkat kemiskinan yang relatif rendah yaitu 250 kab/kota, cluster 1 menunjukkan tingkat kemiskinan yang tinggi yaitu 330 kab/kota , Sedangkan algoritma K-Medoids menghasilkan tiga klaster dengan tingkat kemiskinan rata-rata yang berbeda: cluster 0 menunjukkan tingkat kemiskinan yang relatif rendah yaitu 270 kab/kota, cluster 1 menunjukkan tingkat kemiskinan yang tinggi yaitu 310 kab/kota. Hal ini dapat menjadi referensi bagi pemerintah untuk meningkatkan perhatian wilayah dengan tingkat kemiskinan tinggi dalam upaya mengurangi tantangan ekonomi yang sedang berlangsung. Dengan menggunakan skor sillhouette, untuk membagi tingkat kemiskinan evaluasi algoritma K-Means dan K-Medoids dilakukan. Algoritma k-means menghasilkan nilai K = 0.284 sedangkan algoritma K-Medoids menghasilkan nilai K = 0.224.
Kajian Model Jaringan Syaraf Tiruan Untuk Memprediksi Secara Dini Tingkat Kelulusan Mahasiswa Rohana, Tatang; Nurlaelasari, Euis; Awal, Elsa Elvira; Novita, Hilda Yulia
Technologia : Jurnal Ilmiah Vol 15, No 4 (2024): Technologia (Oktober)
Publisher : Universitas Islam Kalimantan Muhammad Arsyad Al Banjari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31602/tji.v15i4.15583

Abstract

ABSTRAKMasalah: Penelitian ini terkait dengan kajian algoritma jaringan syaraf tiruan untuk memprediksi secara dini tingkat kelulusan mahasiswa. Tujuan: Tujuan penelitian untuk mendeteksi atau memprediksi tingkat kelulusan mahasiswa yang lulus  tepat waktu, sehingga hasilnya diharapkan bisa memberikan kontribusi bagi progam studi dalam menganalisa tingkat kelulusan mahasiswa.Metode: Algoritma yang dipakai meliputi Multilayer Perceptron, Support Vector Machine, dan Decision Tree. Kemudian akan dibandingkan algoritma mana yang memiliki tingkat akurasi yang terbaik dalam memprediksi tingkat kelulusan mahasiswa.Hasil: Berdasarkan hasil penelitian, model Decision Tree memiliki tingkat error rate yang paling baik yaitu 0, model Support Vector Machine sebesar 0.011, dan Multilayer Perceptron 0.029. Berdasarkan  hasil uji performansi dengan Confusion Matrix, model Multilayer Perceptron  memiliki akurasi sebesar 97,1%, Support Vector  Machine 98,9%, dan Decision Tree memiliki akurasi 100%.Kesimpulan: Model Decision Tree memiliki tingkat akurasi terbaik, sehingga algoritma tersebut bisa digunakan dalam membuat sistem  prediksi kelulusan mahasiswa tepat waktu. Untuk penelitian selanjutnya, disarankan untuk menambahkan lebih banyak data mahasiswa agar hasil penelitian bisa lebih baik. Variabel data set juga bisa diperluas tidak hanya dari aspek akademik mahasiswa, tetapi juga dari aspek non-akademik dan latar belakang ekonomi keluarga, seperti pendapatan orang tua, status pekerjaan mahasiswa, dan variabel lainnya.Kata kunci: Jaringan Syaraf, Prediksi, Multilayer Perceptron, Support Vector Machine, Decision Tree  
Analisis Prediksi Banjir di Indonesia Menggunakan Algoritma Support Vector Machine dan Random Forest Purnomo, Indarto Aditya; Indra, Jamaludin; Awal, Elsa Elvira; Rohana, Tatang
Journal of Information System Research (JOSH) Vol 6 No 1 (2024): Oktober 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i1.5958

Abstract

Natural disasters frequently occur in Indonesia, such as floods, landslides, and volcanic eruptions. Geological factors, such as the convergence of four major tectonic plates, make Indonesia vulnerable to natural disasters. Statistical data from the National Disaster Management Agency show an increase in flood occurrences each year, peaking in 2021 with 1,794 incidents. Early anticipation is necessary to minimize the impact of natural disasters, and predictive patterns are becoming new knowledge for preventing and managing these disasters. This study applies the Support Vector Machine and Random Forest algorithms. The results of this study predict that the largest number of floods from 2024 to 2026 in Indonesia will occur in Aceh with 240 floods, North Sumatra with 215 floods, West Java with 210 floods, and Central Java with 160 floods. The best algorithm comparison results were achieved with Random Forest, which had an accuracy of 99.6% and an average RMSE value of 3.834.
Identification of Tajweed Recognition using Wavelet Packet Adaptive Network based on Fuzzy Inference Systems (WPANFIS) Siregar, Ratu Mutiara; Satria, Budy; Prayogi, Andi; Pane, Muhammad Akbar Syahbana; Awal, Elsa Elvira; Sari, Yessi Ratna
Internet of Things and Artificial Intelligence Journal Vol. 4 No. 1 (2024): Volume 4 Issue 1, 2024 [February]
Publisher : Association for Scientific Computing, Electronics, and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/iota.v4i1.703

Abstract

This research aims to develop a system capable of processing voice input to recognize Al-Quran reading by recitation of Tajwid, using wavelet signal extraction and classification of Tajwid rules using ANFIS. The process stages include data acquisition, audio data pre-processing, extraction using wavelet packets, division of training data and test data, and classification. The data obtained were 20 observations from 10 observations carried out in data pre-processing. The wavelet decomposition process produces six main features as ANFIS input variables and 64 rules. Then the data was separated into 17 observations for training data and three for testing data. The test results obtained from the training that had been carried out produced plots that were too fit; in this experiment, the WPANFIS classification model got 100% appropriate classification and SSE values that were the same as the training result, 0.00081225.
Perbandingan Algoritma Generalized Linear Model Dan Linear Regression Untuk Prediksi Hujan Berbasis Data Kaggle Irawan, Muhamad Anggi; Juwita, Ayu Ratna; Awal, Elsa Elvira; Rohana, Tatang
Jurnal Pendidikan dan Teknologi Indonesia Vol 5 No 9 (2025): JPTI - September 2025
Publisher : CV Infinite Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jpti.967

Abstract

Prediksi curah hujan sangat penting bagi berbagai aktivitas yang dipengaruhi kondisi cuaca, khususnya di negara beriklim tropis mengalami kondisi ini secara signifikan. Prediksi curah hujan yang akurat sangat penting untuk mendukung berbagai aspek  perencanaan  kota,  termasuk  pengelolaan  sumber  daya  air  dan  mitigasi  risiko  bencana banjir. Penelitian ini membandingkan dua algoritma machine learning, Generalized Linear Model (GLM) dan Linear Regression, dalam memprediksi curah hujan berdasarkan fitur cuaca seperti suhu, kelembaban, tekanan, angin, tutupan awan, dan data historis. Selanjutnya diproses melalui encoding yang dimana akan mengubah nilai kategorikal menjadi nilai numerik, normalisasi yang melibatkan penyesuaian ulang nilai nilai dalam dataset, dan penanganan class imbalance untuk melakukan duplikasi sample pada kelas minotitas. Setelah dibagi menjadi data latih dan uji, kedua algoritma diterapkan dan dievaluasi menggunakan akurasi, RMSE, dan MAE. Hasilnya, GLM memiliki akurasi sebesar 90.17% lalu untuk RMSE sebesar 0.3949 dan MAE 0.3836, se  dangkan Linear Regression lebih baik dalam nilai MAE sebesar 0.2656  dan RMSE 0.3218 untuk akurasi sebesar 89.26%. Dengan pendekatan analisis yang tepat, pola tersebut dapat dimanfaatkan untuk mendukung keputusan dan perencanaan secara lebih terarah.
Co-Authors AA Sudharmawan, AA Baihaqi, Kiki Ahmad Faisal, Sutan Fitri Nur Masruriyah, Anis Hananto, Agustia Imas Sukaesih Sitanggang Indra, Jamaludin Irawan, Muhamad Anggi Juwita, Ayu Ratna Lailan Syaufina Laurentzia, Rini Beatrix Muhammad Afrizal Amrustian Muhammad Akbar Syahbana Pane Muliati, Vika Febri Munzi, Gugy Guztaman Nisa Utami, Nisa Novalia, Elfina Novita, Hilda Yulia Nurlaelasari, Euis Nurlaila, Diah Pratiwi, Gita Risky Prayogi, Andi Purnomo, Indarto Aditya Rachmawati, Dhea Ratu Mutiara Siregar Rohana, Tatang Sari, Yessi Ratna Setiawan, Pratama Wahyu TARMUJI TARMUJI, TARMUJI Tri Vicika, Vikha Wahiddin, Deden Waiddin, Deden Yana Cahyana