Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Jurnal Dimensi Pratama Teknik Sipil Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Indonesian Journal of Chemical Science
Kevin Wijaya, Kevin
Jurusan Teknologi Informasi, Fakultas Teknik, Universitas Udayana
Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Engineering Physics

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

Found 3 Documents
Search

 1 
KINERJA SISTEM TUNGGAL STRUKTUR BAJA RANGKA TERBREIS EKSENTRIS BERBENTUK V TERBALIK PADA MID RISE BUILDIN Wijaya, Kevin; Ongkowidjojo, Alberto Orson; Tanojo, Effendy; Santoso, Hasan
Jurnal Dimensi Pratama Teknik Sipil Vol 7, No 2 (2018): AGUSTUS 2018
Publisher : Jurnal Dimensi Pratama Teknik Sipil

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (369.664 KB)

Abstract

Indonesia merupakan salah satu negara yang rawan terkena gempa, sehingga bangunan di Indonesia harus didesain tahan terhadap gempa. Dalam penelitian ini, bangunan didesain menggunakan sistem tunggal dengan menggunakan Rangka Terbreis Eksentris (RTE). Sistem tunggal memilki batasan ketinggian dalam SNI 1726:2012 tabel 9, untuk Kategori Desain Seismik D adalah 48 m (12 lantai). Namun, batasan ketinggian tersebut boleh ditinggikan menjadi 72 m (18 lantai) dengan mengikuti persyaratan sesuai dengan SNI 1726:2012 Pasal 7.2.5.4. Oleh karena itu, penelitian ini dilakukan menggunakan mid-rise building, yaitu 12,15, dan 18 lantai, dengan bresing bentuk V terbalik dan dengan menggunakan dua jenis bentang yaitu bangunan 3 bentang dan bangunan 5 bentang. Hasil penelitian menunjukkan seluruh bangunan mengalami kegagalan pada balok link, ini seusai dengan hirarki desain daripada RTE. Dengan semakin tinggi bangunan maka performa bangunan semakin buruk. Ini bisa dilihat dari hasil displacement dan drift ratio. Pada bangunan 3 bentang menghasilkan nilai displacement yang lebih baik namun menghasilkan menghasilkan nilai drift ratio yang lebih buruk dari bangunan 5 bentang. Namun seluruh bangunan masih dalam satu kategori klasifikasi kerusakan bangunan yaitu collapse prevention. Sendi plastis yang terjadi pada semua bangunan menghasilkan lokasi dan jumlah yang relatif sama sehingga disimpulkan seluruh bangunan memiliki kinerja yang relatif sama.
Sentiment Analysis of ChatGPT on Indonesian Text using Hybrid CNN and Bi-LSTM Prasetyo, Vincentius Riandaru; Naufal, Mohammad Farid; Wijaya, Kevin
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 2 (2025): April 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i2.6334

Abstract

This study explores sentiment analysis on Indonesian text using a hybrid deep learning approach that combines Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM). Due to the complex linguistic structure of the Indonesian language, sentiment classification remains challenging, necessitating advanced methods to capture both local patterns and sequential dependencies. The primary objective of this research is to improve sentiment classification accuracy by leveraging a hybrid model that integrates CNN for feature extraction and Bi-LSTM for contextual understanding. The dataset consists of 800 manually labeled samples collected from social media platforms, preprocessed using case folding, stop word removal, and lemmatization. Word embeddings are generated using the Word2Vec CBOW model, and the classification model is trained using a hybrid architecture. The best performance was achieved with 32 Bi-LSTM units, a dropout rate 0.5, and L2 regularization, which was evaluated using Stratified K-Fold cross-validation. Experimental results demonstrate that the hybrid model outperforms conventional deep learning approaches, achieving 95.24% accuracy, 95.09% precision, 95.15% recall, and 95.99% F1 score. These findings highlight the effectiveness of hybrid architectures in sentiment analysis for low-resource languages. Future work may explore larger datasets or transfer learning to enhance generalizability.
implications of adding chitosan and glycerol to edible film from sweet potato starch on tensile strength Wijaya, Kevin; Tantra Diwa Larasati
Indonesian Journal of Chemical Science Vol. 14 No. 2 (2025): Indonesian Journal of Chemical Science
Publisher : Prodi Kimia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ijcs.v14i2.6906

Abstract

The use of inappropriate plastic in food packaging can pose risks to human health, including the potential for cancer, because the plastic raw materials come from natural gas and petroleum. Even though it is still used, the use of this material is starting to be reduced because its impact is not environmentally friendly and has the potential to be detrimental to health. One innovation that can be implemented is the use of edible organic plastic, such as edible film. The development of edible film materials involves polymer compounds from plants, such as starch. This research aims to find the best formulation for making edible film using various variations of chitosan addition. Edible film is made from sweet potato starch with the addition of 3% variable composition chitosan; 4%; 5% (w/v) and glycerol (3%). Tests show that the higher the chitosan content in starch, the Tensile Strength (TS) of edible film will increase. Findings from the research show that the best edible film is produced from sweet potato starch with a chitosan variation of 5% (w/v).
Co-Authors Effendy Tanojo Hasan Santoso Mohammad Farid Naufal, Mohammad Farid Ongkowidjojo, Alberto Orson Tantra Diwa Larasati Vincentius Riandaru Prasetyo