Article Per Year (5 Year)
p-Index From 2021 - 2026
0.659
P-Index
This Author published in this journals
All Journal JIPI (Jurnal Ilmu Perpustakaan dan Informasi) Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Indonesian Journal on Software Engineering (IJSE)
Suhardi Aras
Universitas Muhammadiyah Sorong
Computer Science & IT Engineering Library & Information Science

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Optimasi Hyperparameter dari CNN Classifier untuk Klasifikasi Genre Musik Rendra Soekarta; Suhardi Aras; Ahmad Nur Aswad
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 7 No 5 (2023): October 2023
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v7i5.5319

Abstract

Playing music through a digital platform that has a large database of songs requires automated classification of music genres, highlighting the need to develop a model for music genre classification that is more efficient and accurate. This study evaluated the hyperparameters in the music genre classification process using CNN in the GTZAN dataset with 30-second duration data optimized using MFCC feature extraction. The model that is formed with a time of 3 (three) seconds classifies music genres in the first 3 seconds of music. This model has a high potential for error because the first 3 seconds of initial music are varied and cannot be used as a benchmark in determining music genres. This study performed hyperparameters on batch size, epoch, and split data set variables with various scenarios. The highest precision result was obtained at 72% with a data split of 85%:15%, 32 batch sizes, and 500 epochs.
DETEKSI PEROKOK DI KAWASAN BEBAS ROKOK MENGGUNAKAN YOLOv5 Muh Fadli Hasa; Suhardi Aras; Filzah Maharani Salsabila; Nurhayati Safitri
Indonesian Journal on Software Engineering (IJSE) Vol 10, No 1 (2024): IJSE 2024 (ON PROGRESS)
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/ijse.v10i1.20205

Abstract

Merokok merupakan kegiatan yang tidak hanya membahayakan kesehatan, namun dapat membawa dampat yang buruk bagi lingkungan, terlebih jika kegiatan merokok tersebut dilakukan tanpa memikirkan peraturan yang berlaku di sekitar. Larangan merokok di kawasan tertentu sudah banyak dibuatkan dalam bentuk tanda peringatan yang dapat dibaca untuk mengingatkan manusia agar tidak merokok di kawasan tersebut. Larangan merokok di wilayah bebas rokok merupakan tindakan penerapan kebijakan untuk melindungi kesehatan masyarakat dan menciptakan lingkungan yang bebas dari asap rokok. Kebijakan ini bertujuan untuk mengurangi dampak negatif merokok, termasuk merokok pasif (inhalasi asap rokok oleh orang lain yang tidak merokok). Larangan merokok di wilayah bebas rokok biasanya diberlakukan di area publik dan tempat tertentu, seperti rumah sakit, temat ibadah, pom bensin, transportasi umum, taman bermain anak, dan lain sebagainya. Seiring dengan perkembangannya jaman, terdapat beberapa solusi yang dapat membantu untuk mengamati kegiatan merokok di kawasan bebas rokok tersebut. Salah satu solusinya adalah denganmemanfaatkan teknologi deep learning. Sistem deteksi objek yang dibuat pada penelitian menggunakan metodedeep learning dengan algoritma YOLOv5 untuk mendeteksi secara real-time. Peneliti menggunakan dataset sebanyak 435 gambar yang kemudian dibagi menjadi train, validation, dan test dengan perbandingan 77:15:8. Berdasarkan pengujian yang telah dilakukan,didapatkan kesimpulan bahwa metode untuk mendeteksi objek berupa rokok ini bekerja secara konsisten dengan tingkat akurasi yang cukup baik.
EXPLORING THE STRENGTHS AND CHALLENGES OF RUMAH KATA SORONG: A STUDY OF A COMMUNITY READING PARK Dayu Rifanto; Jajat Sudrajat Ardiwinata; Joni Rahmat Pramudia; Suhardi Aras
JIPI (Jurnal Ilmu Perpustakaan dan Informasi) Vol 10, No 2 (2025)
Publisher : Progam Studi Ilmu Perpustakaan UIN Sumatera Utara Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/jipi.v10i2.25954

Abstract

Papua still faces significant literacy challenges, and Community reading parks (TBMs), such as Rumah Kata Sorong (RKS), play a vital role in addressing these challenges by promoting literacy and fostering a reading culture. However, there is a lack of specific research on TBMs in Papua. Thus, a SWOT analysis of RKS is essential to develop strategic recommendations for its growth and improved impact on local literacy. This study uses a descriptive-analytical qualitative approach to explore Rumah Kata Sorong, focusing on its founder and volunteers, and aims to develop strategic recommendations to strengthen TBMs and enhance community literacy. Rumah Kata Sorong stands out among community reading parks with its curated book collection, diverse facilities, and community-driven initiatives like reading clubs and literary workshops, while also facing challenges such as limited volunteers and financial sustainability. In conclusion, RKS distinguishes itself by offering a unique collection of books, fostering reading communities, and addressing challenges such as limited management and volunteer support. The study contributes by providing a replicable model for strengthening TBMs in other regions, and by expanding the understanding of community-based literacy development in areas like Papua. Future research could explore the program's impact through quantitative analysis of community involvement and outcomes.
Co-Authors Ahmad Nur Aswad Dayu Rifanto Filzah Maharani Salsabila Jajat S. Ardiwinata, Jajat S. Muh. Fadli Hasa Nurhayati Safitri Pramudia, Joni Rahmat Soekarta, Rendra