Article Per Year (5 Year)
p-Index From 2020 - 2025
0.817
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Jurnal Teknik Informatika International Journal for Educational and Vocational Studies Journal of Electronics, Electromedical Engineering, and Medical Informatics
Sambul, Alwin Melkie
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering Environmental Science Languange, Linguistic, Communication & Media Library & Information Science Mathematics Social Sciences

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Waste Transportation Route Optimization in Manado using A-Star Algorithm (A*) Mananoma, Yosua; Sentinuwo, Steven Ray; Sambul, Alwin Melkie
Jurnal Teknik Informatika Vol 16, No 3 (2021): JURNAL TEKNIK INFORMATIKA
Publisher : Universitas Sam Ratulangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35793/jti.16.3.2021.34193

Abstract

Abstract —Sampah merupakan benda yang sudah tidak terpakai oleh manusia dan kemudian akan dibuang. Sampah di setiap lingkungan daerah pada umumnya ditampung di Tempat Pembuangan Sementara (TPS) Kemudian di angkut oleh armada pengangkut sampah untuk dibawah ke Tempat Pembuangan Akhir (TPA). Proses pengangkutan sampah dipengaruhi oleh pola pengangkutan dan waktu tempuh pengangkutan. Oleh karena itu untuk meningkat keefesienan perlu adanya penentuan rute optimal yang menghasilkan jalur terpendek pengangkutan sampah. Salah satu cara implementasi adalah menggunakan algoritma a-star untuk memperoleh rute terpendek saat pengangkutan dan menggukan metode waterfall dalam pengembangan sistem. Algoritma a-star bekerja menganalisa setiap jalur yang dikunjungi kemudian menghasilkan solusi terbaik menuju titik tujuan. Penentuan rute optimal pengangkutan sampah menghasilkan rute yang bisa dipertimbangkan untuk dilalui dengan menempuh jarak yang terpendek menuju ke titik tujuan sehingga dapat meningkatkan keefektifan, mengurangi biaya dan meningkatkan pelayanan. Abstract — Waste is an obejct that is not uset by humans, and will then be thrown away. Garbage in each regional environment is generally accomodated in a temporary landfills and will be transported ti a landfukk. The process of transporting waste is influenced by the pattern of transportation and the travel time. Therefore, to increase efficiency, it is necessary to determine the optimal route which results in the shortest route for transporting waste. The implementation using a-star algorithm to get the shortest route and use the waterfall method for system development. A-star algorithm works to analyze each route and produces the best solution to destination point. Determining the optimal route for waste transportation results in a route that can be considered to be followed by traveling the shortest distance to the destination point so as to increase effectiveness, reduce costs and improve service.
Comparative Analysis of Hepatitis C virus Genotype 1a (Isolate 1) using Multiple Regression Algorithms and Fingerprinting Techniques Nur Fiat, Daffa; Suratinoyo, Syifabela; Kolang, Indri Claudia; Ticoalu, Injilia Tirza; Purnomo, Nadira Tri Ardianti; Mawara, Reza Michelly Cantika; Sengkey, Daniel; Masengi, Angelina Stevany Regina; Sambul, Alwin Melkie
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 6 No 4 (2024): October
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v6i4.506

Abstract

Approximately 70 million people worldwide have been infected with Hepatitis C virus (HCV), presenting a critical global health challenge. As a member of the Flaviviridae family, HCV can cause severe liver diseases such as cirrhosis, acute hepatitis, and chronic hepatitis. The Hepatitis C virus (HCV) genome encodes a single polyprotein consisting of 3010 amino acids, which when processed contains 10 polypeptides derived from cellular and viral proteases. These include structural proteins such as core protein, E1 and E2 envelope glycoproteins, and nonstructural proteins such as NS1, NS2, NS3, NS4A, NS4B, NS5A, and NS5B. Nonstructural proteins will be released by HCV NS2-3 and NS3-4A proteases, however, structural proteins will be released by host ER signaling peptidases. co-translationally and post-translationally form 10 individual structural proteins: 5'-C-E1-E2-p7-NS2-NS3-NS4A-NS4B-NS5A-NS5B-3'. Despite extensive research, there are significant gaps in predictive and analytical approaches to managing HCV, particularly in understanding the polyprotein structure and its implications for drug discovery. This study addresses these gaps by employing machine learning techniques to analyze HCV polyprotein using various fingerprinting methods and regression algorithms. The data was sourced from the ChEMBL database, and fingerprinting techniques such as PubChem, MACCS, and E-State were utilized. Regression algorithms, including Gradient Boosting Regression (GBR), Random Forest Regression (RFR), AdaBoost Regression (ABR), and Hist Gradient Boosting Regression (HSR), were applied. Model performance was evaluated using R² and Adjusted R² metrics, comparing default models with those enhanced by hyperparameter tuning. Feature importance analysis was conducted to identify key features influencing model performance, aiding in model simplification. The results show that although hyperparameter tuning does not significantly improve the predictive power of a model, it can provide an insight into model optimization. In particular, the default model showed higher R² and Adjusted R² values across different fingerprinting techniques compared to models with hyperparameterized features. Gradient Boosting Regression (GBR) and Random Forest Regression (RFR) consistently performed well, with GBR showing the highest R² values when using PubChem fingerprints. Although there was no significant improvement through hyperparameter tuning, this study was able to find out the features that strongly influenced the model performance by conducting a feature importance analysis. This analysis helped simplify the model and highlighted the potential of machine learning in improving the understanding of HCV polyprotein structure. This research identifies optimal regression models and fingerprinting techniques, providing a strong framework for future drug discovery efforts aimed at improving global health outcomes. The research also shows that it is important to date to advance drug discovery using machine learning.
Aplikasi Kecerdasan Artifisial Generatif Untuk Asesmen Pembelajaran Berdasarkan Rubrik: An Application of Generative Artificial Intelligence for Automated Rubric-Based Grading Legi, Moudy; Sengkey, Daniel Febrian; Sambul, Alwin Melkie
Jurnal Teknik Informatika Vol. 19 No. 03 (2024): Jurnal Teknik Informatika
Publisher : Universitas Sam Ratulangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35793/jti.v19i3.53916

Abstract

Abstract — Improving the effectiveness of learning assessments is essential in modern education. Therefore, the use of rubrics as an assessment tool has become crucial. This research aims to develop a web application that facilitates the learning assessment process using rubrics. The main issues faced in conventional assessment processes are inefficiency, especially in providing accurate and prompt feedback to learners, and the time-consuming process of creating rubrics. Hence, a solution is needed to enhance the assessment process by leveraging technology. The system development method used is the System Development Life Cycle (SDLC) with an Agile approach. The web application is built using the Flask framework, with integration of OpenAI’s ChatGPT to support automated assessment using rubrics. This application is designed to assist teachers in creating, saving, and managing rubrics efficiently. The research involves stages of needs analysis, design, development, testing, and evaluation. The developed web application successfully provides a solution to enhance the learning assessment process. Features such as automatic rubric creation and automated assessment improve assessment efficiency. This research makes a positive contribution to the development of technology in the context of learning and assessment. Keywords — artificial intelligence; chatgpt; flask; generative artificial intelligence; rubric assessment; web                 Abstrak — Meningkatkan efektivitas penilaian pembelajaran sangat penting dalam Pendidikan modern. Oleh karena itu, penggunaan rubrik sebagai alat penilaian telah menjadi hal yang krusial. Penelitian ini bertujuan untuk mengembangkan aplikasi yang memfasilitasi proses penilaian pembelajaran menggunakan rubrik. Masalah utama yang dihadapi dalam proses penilaian konvensional adalah ketidakefisienan, terutama dalam memberikan umpan balik yang akurat dan cepat kepada peserta didik, serta proses pembuatan rubrik yang memakan waktu. Oleh karena itu, diperlukan Solusi untuk meningkatkan proses penilaian dengan memanfaatkan teknologi. Metode pengembangan sistem yang digunakan adalah Siklus Hidup Pengembangan Sistem dengan pendekatan Agile. Aplikasi ini dibangun menggunakan kerangka kerja Flask, dengan integrasi ChatGPT dari OpenAI untuk mendukung penilaian otomatis menggunakan rubrik. Aplikasi ini dirancang untuk membantu guru dalam membuat, menyimpan, dan mengelola rubrik secara efisien. Penelitian melibatkan tahapan analisis, desain, pengembangan, pengujian, dan evaluasi. Aplikasi yang dikembangkan berhasil memberikan Solusi untuk meningkatkan proses penilaian pembelajaran. Fitur-fitur seperti pembuatan rubrik otomatis dan penilaian otomatis meningkatkan efisiensi penilaian. Penelitian ini memberikan kontribusi positif terhadap pengembangan teknologi dalam konteks pembelajaran dan penilaian.               Kata Kunci — ChatGPT; Flask; kecerdasan artifisial; kecerdasan artifisial generatif; penilaian rubrik; web
A Survey on Students Interests toward On-line Learning Media Choices: A Case Study Sengkey, Daniel Febrian; Paturusi, Sary Diane Ekawati; Sambul, Alwin Melkie; Gozali, Chyntia Theresa
International Journal for Educational and Vocational Studies Vol. 1 No. 2 (2019): June 2019
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/ijevs.v1i2.1527

Abstract

The advancement of Information Technology alters various aspects of human life, including learning. In the present era, on-line learning facilities are provided by institutions, ranging from formal higher education to open course-ware providers. On-line learning or e-learning is mostly achieved through stored media that widely available. These media take forms in various formats such as text and images, slide that equipped with narration from the lecturer, or a video where the lecturer appears inside the frames. We conducted a research about how students would response to the available learning media. The research was conducted with repetitive measures. Each measurement was a module that divided into three parts, where each part was presented to the student as one out of three media listed above. Hence we had three media types for each module. Each module took one week, and at the next week we gather their responses through evaluation forms. All modules were completed in six consecutive weeks. After all modules were completed, we analyze their responses and found that our samples responded best to the video with the appearance of the instructor/lecturer, then the slide with audio, and finally text and images.
Investigation on low-performance tuned-regressor of inhibitory concentration targeting the SARS-CoV-2 polyprotein 1ab Sengkey, Daniel Febrian; Regina Masengi, Angelina Stevany; Sambul, Alwin Melkie; Tallei, Trina Ekawati; Unsratdianto Sompie, Sherwin Reinaldo
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 4: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i4.pp3003-3013

Abstract

Hyperparameter tuning is a key optimization strategy in machine learning (ML), often used with GridSearchCV to find optimal hyperparameter combinations. This study aimed to predict the half-maximal inhibitory concentration (IC50) of small molecules targeting the SARS-CoV-2 replicase polyprotein 1ab (pp1ab) by optimizing three ML algorithms: histogram gradient boosting regressor (HGBR), light gradient boosting regressor (LGBR), and random forest regressor (RFR). Bioactivity data, including duplicates, were processed using three approaches: untreated, aggregation of quantitative bioactivity, and duplicate removal. Molecular features were encoded using twelve types of molecular fingerprints. To optimize the models, hyperparameter tuning with GridSearchCV was applied across a broad parameter space. The results showed that the performance of the models was inconsistent, despite comprehensive hyperparameter tuning. Further analysis showed that the distribution of Murcko fragments was uneven between the training and testing datasets. Key fragments were underrepresented in the testing phase, leading to a mismatch in model predictions. The study demonstrates that hyperparameter tuning alone may not be sufficient to achieve high predictive performance when the distribution of molecular fragments is unbalanced between training and testing datasets. Ensuring fragment diversity across datasets is crucial for improving model reliability in drug discovery applications.
Co-Authors Angelina Stevany Regina Masengi Daniel Febrian Sengkey Gozali, Chyntia Theresa Kolang, Indri Claudia Legi, Moudy Mananoma, Yosua Mawara, Reza Michelly Cantika Nur Fiat, Daffa Paturusi, Sary Diane Ekawati Purnomo, Nadira Tri Ardianti Steven Ray Sentinuwo Suratinoyo, Syifabela Ticoalu, Injilia Tirza TRINA EKAWATI TALLEI Unsratdianto Sompie, Sherwin Reinaldo