Article Per Year (5 Year)
p-Index From 2021 - 2026
1.817
P-Index
This Author published in this journals
All Journal Sinkron : Jurnal dan Penelitian Teknik Informatika Jatilima : Jurnal Multimedia Dan Teknologi Informasi Sisfo: Jurnal Ilmiah Sistem Informasi Lentera AMMA : Jurnal Pengabdian Masyarakat Jurnal Ilmu Komputer Aceh
Asrawi, Hannan
Unknown Affiliation
Humanities Chemistry Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Engineering Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mechanical Engineering Nursing Social Sciences

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 11 Documents
Search

 1   2 
The LSTM and Bidirectional GRU Comparison for Text Classification Asrawi, Hannan; Utami, Ema; Yaqin, Ainul
Sinkron : jurnal dan penelitian teknik informatika Vol. 7 No. 4 (2023): Article Research Volume 7 Issue 4, October 2023
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v8i4.12899

Abstract

Although the phrases machine learning and AI are frequently used interchangeably and are frequently discussed together, they do not have the same meanings. While all artificial intelligence (AI) is machine learning, not all AI is machine learning, which is a key distinction. In the beginning, machine learning and natural language processing (NLP) are related since machine learning is frequently employed as a tool for NLP tasks. The advantage of NLP is that it can perform analysis, and examine a lot of data, including comments on social media accounts and hundreds of online customer evaluations. Text classification is essentially what needs to be done. This study compares Bidirectional GRU and LSTM as text classification algorithms using 20,000 newsgroup documents from 20 newsgroups from The UCI KDD Archive. After using the suggested model, we compare it to the long short-term memory and bidirectional GRU models for accuracy and validation. The results of the two comparisons show that the bidirectional GRU model performs better than the long short-term memory model. And this is a successful classification of text using a deep learning algorithm that uses a bidirectional GRU.
Implementasi Long Short Term Memory pada klasifikasi Teks Asrawi, Hannan
Lentera : Jurnal Ilmiah Sains, Teknologi, Ekonomi, Sosial, dan Budaya Vol. 9 No. 1: Lentera, Februari 2025
Publisher : LPPM Universitas Almuslim

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

Abstract

Meskipun keduanya terkadang digunakan secara bergantian, istilah “pembelajaran mesin” dan “AI” memiliki arti yang berbeda. Tidak semua kecerdasan buatan adalah pembelajaran mesin adalah perbedaan yang signifikan di antara keduanya. Pada awalnya, machine learning dan natural language processing (NLP) saling berkaitan karena machine learning sering digunakan sebagai alat bantu untuk tugas-tugas NLP. Keuntungan dari NLP adalah dapat melakukan analisis dan memeriksa banyak data, termasuk komentar di akun media sosial dan ratusan evaluasi pelanggan online. Penelitian ini menggunakan Long Short Term Memory sebagai algoritma klasifikasi teks dengan menggunakan 18.000 dokumen newsgroup dari 20 newsgroup dari The UCI KDD Archive.
Penerapan Teorema Bayes Pada Sistem Pakar Untuk Mendiagnosa Penyakit Ayam Berbasis Web Sri Winar; Hannan Asrawi; Rekha Audina; Riyadhul Fajri
Sisfo: Jurnal Ilmiah Sistem Informasi Vol. 9 No. 1 (2025): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2025
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/sisfo.v9i1.22135

Abstract

Teknologi mempunyai peranan penting yang tentunya tidak terlepas kaitannya dengan Teknologi Informasi (TI). Komputer merupakan satu bagian paling penting dalam peningkatan Teknologi Informasi, dengan menyimpan infomasi aturan penalaran yang memadai, memungkinkan komputer memberikan kesimpulan atau pengambil keputusan yang kualitasnya sama dengan kemampuan seorang pakar bidang ilmu pengetahuan tertentu. Salah satu cabang ilmu Teknik Informatika yang dapat mendukung tersebut adalah sistem pakar. Sistem pakar adalah salah satu bidang kecerdasan buatan yang menggabungkan pengetahuan dan penelusuran data untuk memecahkan masalah secara normal memerlukan keahlian manusia. Sampai saat ini sudah ada beberapa hasil perkembangan sistem pakar dalam berbagai bidang sesuai dengan bidang kepakaran seseorang, misalnya bidang kedokteran, pendidikan ataupun pertanian dan peternakan. Hasil penelitian ini untuk bidang peternakan seperti yang diusulkan dalam didasarkan atas banyaknya peternak ayam yang mengalami kerugian karena tidak mengetahui penyakit apa yang menjangkiti ternaknya, khususnya peternak pemula yang masih awam dibidang peternakan.
IMPLEMANTASI FITUR EKSTRAKSI GLOVE PADA TEKS KLASIFIKASI MENGGUNAKAN ALGORITMA LONG-SHORT TERM MEMORY Asrawi, Hannan; Sriwinar; Bilqisthi, Muhammad Fataya
Jurnal Multimedia dan Teknologi Informasi (Jatilima) Vol. 7 No. 03 (2025): Jatilima : Jurnal Multimedia Dan Teknologi Informasi
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jatilima.v7i03.1694

Abstract

Perkembangan pesat data digital menuntut metode cerdas untuk mengelompokkan teks secara otomatis dan akurat. Salah satu pendekatan yang menjanjikan adalah memadukan representasi kata berbasis word embedding dengan model deep learning yang mampu memahami konteks urutan kata. Mengkaji klasifikasi teks dengan menggabungkan fitur ekstraksi GloVe dan algoritma Long Short-Term Memory (LSTM) untuk mengelompokkan dokumen berita dari dataset 20 Newsgroups. Teks terlebih dahulu melalui pra-pemrosesan pembersihan tanda baca, case folding, penghapusan stopword, tokenisasi, dan stemming lalu setiap kata direpresentasikan sebagai vektor berdimensi tetap menggunakan model GloVe yang mampu menangkap makna dan hubungan semantik secara global. Vektor ini menjadi masukan jaringan LSTM yang belajar mengenali pola urutan kata dan konteks topik. Evaluasi dengan metrik akurasi, presisi, recall, dan F1-score menunjukkan kinerja tinggi: akurasi 0,9562, presisi 0,9701, recall 0,9485, dan F1-score 0,9701. Hasil ini menegaskan bahwa kombinasi GloVe dan LSTM efektif serta kompetitif, mampu menghasilkan klasifikasi teks yang presisi dan seimbang, sehingga layak diterapkan pada berbagai aplikasi pemrosesan bahasa alami yang memerlukan pengelompokan dokumen secara otomatis dan akurat.
Implementasi Long Short Term Memory pada klasifikasi Teks Asrawi, Hannan
Lentera : Jurnal Ilmiah Sains, Teknologi, Ekonomi, Sosial, dan Budaya Vol. 9 No. 1: Lentera, Februari 2025
Publisher : LPPM Universitas Almuslim

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

Abstract

Meskipun keduanya terkadang digunakan secara bergantian, istilah “pembelajaran mesin” dan “AI” memiliki arti yang berbeda. Tidak semua kecerdasan buatan adalah pembelajaran mesin adalah perbedaan yang signifikan di antara keduanya. Pada awalnya, machine learning dan natural language processing (NLP) saling berkaitan karena machine learning sering digunakan sebagai alat bantu untuk tugas-tugas NLP. Keuntungan dari NLP adalah dapat melakukan analisis dan memeriksa banyak data, termasuk komentar di akun media sosial dan ratusan evaluasi pelanggan online. Penelitian ini menggunakan Long Short Term Memory sebagai algoritma klasifikasi teks dengan menggunakan 18.000 dokumen newsgroup dari 20 newsgroup dari The UCI KDD Archive.
Pelatihan Desain Grafis Menggunakan Aplikasi Canva Untuk Siswa Di SMK Kesehatan Binatama Abd Mizwar A. Rahim; Theopilus Bayu Sasongko; Hannan Asrawi
AMMA : Jurnal Pengabdian Masyarakat Vol. 3 No. 11 : Desember (2024): AMMA : Jurnal Pengabdian Masyarakat
Publisher : CV. Multi Kreasi Media

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

Abstract

Technological development is an important factor as a driver of growth and progress in a country. Technology today plays a very important role, especially in the field of education. One way to deal with this is utilizing technology, which can be done by starting to introduce technology to students at an early age through graphic design using the Canva app. In the environment of SMK Kesehatan Binatama, the use of technology in teaching activities has not been done effectively. Learning activities are still done normally without frequently using technology, so it is necessary to have Canva training as a form of technology adaptation and a means to channel the creativity of the students. The methods used are training methods that include material delivery, practice, and evaluation. Training activities run smoothly: each student can follow a whole range of activities from start to finish, and each student may create one graphic design independently.
Analisis Prediktif Tingkat Kematangan Alpukat Menggunakan Algoritma Logistic Regression Natasya Aulia; Iqbal Iqbal; Hannan Asrawi
Jurnal Ilmu Komputer Aceh Vol 3 No 1 (2026): Jurnal Ilmu Komputer Aceh
Publisher : Fakultas Ilmu Komputer Universitas Almuslim

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

Abstract

Determining the ripeness level of avocado fruit is an important factor in distribution, marketing, and consumption processes. Conventional ripeness assessment is often subjective and dependent on human experience, which can lead to inconsistent results. This study aims to develop an avocado ripeness prediction system using the Logistic Regression algorithm based on physical and visual fruit characteristics. The dataset consists of 1,250 avocado samples with features including firmness, color attributes, tapping sound, weight, and fruit size. Data preprocessing involved cleaning, normalization of numerical features using StandardScaler, and categorical feature transformation using one-hot encoding. The experimental results show that the proposed model achieved an accuracy of approximately 77% in classifying avocado ripeness into ripe and unripe categories, indicating that Logistic Regression is a lightweight and efficient approach for numerical-based ripeness prediction systems.
Klasifikasi Kelayakan Penerimaan Beasiswa Kip Menggunakan Metode Decision Tree Nafira; Iqbal Iqbal; Hannan Asrawi
Jurnal Ilmu Komputer Aceh Vol 3 No 1 (2026): Jurnal Ilmu Komputer Aceh
Publisher : Fakultas Ilmu Komputer Universitas Almuslim

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

Abstract

The KIP Kuliah program aims to improve access to higher education for students from underprivileged families. The scholarship selection process, which is often conducted manually, tends to be inefficient and prone to subjectivity. This study aims to develop a classification model using the Decision Tree C4.5 algorithm based on a data mining approach. The dataset includes parents’ income, parents’ occupation and education, number of dependents, home ownership and condition, electricity capacity, house size, and achievement data. The research stages include data collection, preprocessing, model development, and evaluation using a confusion matrix and performance metrics such as accuracy, precision, recall, and f1-score. The results show that the model achieves an accuracy of 98%. Parents’ income and number of dependents are the most influential factors in determining eligibility. The resulting model has a simple structure, making it easy to interpret and useful for supporting a more objective and efficient selection process.
Pengembangan Sistem Notifikasi Informasi Terbaru PKBM Putra Peusangan Menggunakan Metode Agile Marwan; Imam Muslem; Hannan Asrawi
Jurnal Ilmu Komputer Aceh Vol 3 No 2 (2026): Jurnal Ilmu Komputer Aceh
Publisher : Fakultas Ilmu Komputer Universitas Almuslim

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

Abstract

The rapid development of information technology in education demands systems capable of delivering academic information quickly and accurately. One of the common problems at PKBM Putra Peusangan is the delay in delivering important information and student grades due to manual processes and limited communication media. This study aims to develop a web-based notification system integrated with a Telegram bot to automate the delivery of academic information to students. The system was developed using the Agile method to ensure flexibility and adaptability to user needs. Data processing is carried out through manual input and Excel file uploads, which are verified before being stored in the database. The results show that the system improves efficiency in information management and accelerates the delivery of notifications in real time. The implementation of this system makes information distribution more effective, transparent, and easily accessible for students.
Sistem Pendukung Keputusan Pemilihan Smartphone Terbaik Menggunakan Metode Copras (Complex Proportional Assessment) Riska Silvia; Sriwinar; Hannan Asrawi
Jurnal Ilmu Komputer Aceh Vol 3 No 2 (2026): Jurnal Ilmu Komputer Aceh
Publisher : Fakultas Ilmu Komputer Universitas Almuslim

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

Abstract

The rapid development of the smartphone industry has resulted in a wide variety of products with different specifications and prices. This condition often makes consumers confused when determining the best smartphone that suits their needs. Therefore, a decision support system is needed to assist users in selecting smartphones objectively based on several technical criteria. This study aims to develop a Decision Support System (DSS) for selecting the best smartphone in the price range of IDR 3–5 million using the Complex Proportional Assessment (COPRAS) method. The research evaluates several smartphone alternatives based on twelve criteria consisting of ten benefit criteria and two cost criteria. The COPRAS method processes the data through normalization, weighting, and utility value calculation to determine the ranking of each alternative. The results of the study show that the proposed system is capable of providing objective recommendations based on the utility value of each smartphone alternative. The system can assist users in making rational and data-driven decisions when selecting smartphones. In addition, the developed model can also be applied to other product selection problems involving multiple criteria.
Co-Authors AA Sudharmawan, AA Abd Mizwar A. Rahim Bilqisthi, Muhammad Fataya Ema Utami Iqbal Iqbal Muslem R, Imam Nafira Natasya Aulia Nurannas Rekha Audina Riska Silvia Riyadhul Fajri Sasongko, Theopilus Bayu Sriwinar Sriwinar Sriwinar