Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi Journal of Pharmaceutical and Sciences.
Surono , Sugiyarto
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Computer Science & IT Decision Sciences, Operations Research & Management Immunology & microbiology Materials Science & Nanotechnology Medicine & Pharmacology Nursing Public Health

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Enhancing Multi-Class Classification of Non-Functional Requirements Using a BERT-DBN Hybrid Model Suris, Badzliana Aqmar; Thobirin, Aris; Surono , Sugiyarto; Abdulnazar, Mohamed Naeem Antharathara
INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi Vol 9 No 2 (2025): August 2025
Publisher : Universitas Nusantara PGRI Kediri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29407/intensif.v9i2.24637

Abstract

Background: Software requirements classification is essential to group Non-Functional Requirements (NFR) into several aspects, such as security, usability, performance, and operability. The main challenges in NFR classification are data limitations, text complexity, and high generalization needs. Objective: This research seeks to create a classification model using a hybrid of BERT and DBN, optimize hyperparameters, and improve data representation. Methods: A BERT and DBN-based approach is used, where DBN enhances BERT's ability to extract hierarchical features. Bayesian Optimization determines the optimal hyperparameters and data augmentation is applied to enrich the dataset variation. The model is tested on the PROMISE dataset consisting of 625 data. Results: The BERT-DBN model achieves 95% accuracy on the baseline configuration and 94% on the extensive configuration, better than the previous model, BERT-CNN. The model shows stability without any indication of overfitting. Conclusion: The combination of data augmentation, hyperparameter optimization, and DBN's ability to capture hierarchical patterns improves the accuracy of NFR classification, making it more effective than existing methods, and is expected to enhance text-based classification for software requirements.
Analisis Efek Samping Obat Anti Tuberkulosis Menggunakan K-Means Clustering di RSUD Prof. Dr. H. Aloei Saboe Kota Gorontalo Hipmi , Ahmad Fahrian; Wijaya , Made Hariadi; Abas , Siti Nur Rahmatiya; Darmawan , Endang; Lolita , Lolita; Irham , Lalu Muhammad; Surono , Sugiyarto
Journal of Pharmaceutical and Sciences JPS Volume 8 Nomor 4 (2025)
Publisher : Fakultas Farmasi Universitas Tjut Nyak Dhien

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36490/journal-jps.com.v8i4.1041

Abstract

Background: The side effects of anti-tuberculosis drugs (OAT) experienced by patients often interfere with their daily activities and affect their compliance in completing relatively long-term treatment. This is one of the reasons patients discontinue OAT therapy unilaterally, which can lead to treatment failure for tuberculosis (TB). Objective: To analyse the side effects of OAT in patients at Prof. Dr. H. Aloei Saboe General Hospital in Gorontalo City using k-means clustering. Methods: Data including gender, age, OAT regimen, laboratory results, comorbidities, and types of OAT side effects were analyzed using the k-means method to determine patient clustering patterns. Research Results: The analysis yielded three clusters. Cluster 1 (25 patients) was predominantly male (80%), aged 45–54 years, received first-line OAT (88%), experienced elevated SGPT/SGOT levels (88%), had hypertension as the most common comorbidity (28%), and primarily experienced liver dysfunction as the main side effect (96%). Cluster 2 (348 patients) was predominantly male (58%), aged 35–44 years, receiving OAT line 1 (96.1%), no increase in SGPT and SGOT levels (0%), almost no increase in urea and creatinine levels (0.2%), the most common comorbidity being diabetes mellitus (22.1%). The main side effect being gastrointestinal disorders (58.9%). Cluster 3 (40 patients) was predominantly male (70%), aged 45–54 years, received OAT line 1 (97.5%), experienced an increase in urea and creatinine levels (97.5%), and the most common comorbidity was diabetes mellitus (47.5%). The main side effect was renal dysfunction (95%). Conclusion: The k-means algorithm is effective in generating clusters of patient characteristics. This clustering supports specific interventions such as comorbidity therapy management and monitoring of side effect risks, thereby optimising individualised tuberculosis (TB) treatment.
Co-Authors Abas , Siti Nur Rahmatiya Abdulnazar, Mohamed Naeem Antharathara Aris Thobirin, Aris Darmawan , Endang Hipmi , Ahmad Fahrian Irham , Lalu Muhammad Lolita , Lolita Suris, Badzliana Aqmar Wijaya , Made Hariadi