Claim Missing Document
Check
Articles

Found 36 Documents
Search

Evaluasi Performa Proof of Work dan Proof of Stake melalui Uji Stres Beban Tinggi Blockchain Yulianti, Indira; Ardiansyah, Rizka; Yazdi Pusadan, Mohammad; Amriana; Lamasitudju, Chairunnisa
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2500

Abstract

Consensus mechanisms play a crucial role in determining the efficiency and scalability of blockchain systems. The two most commonly used algorithms are Proof of Work and Proof of Stake, each exhibiting distinct performance characteristics under high transaction loads. This study aims to evaluate and compare the performance of both consensus mechanisms through a simulation-based experimental approach. Testing was conducted using the Hardhat framework in a local environment under two primary scenarios: transaction scaling and burst transaction.Four evaluation metrics were employed: throughput, transaction latency, finality time, and mempool congestion. The results indicate that Proof of Stake consistently outperforms across all four metrics, demonstrating high throughput, stable latency and finality time, and controlled mempool congestion. In contrast, Proof of Work shows a significant decline in performance under heavy load due to its static and non-adaptive mining process.The Mann-Whitney U statistical test confirms that the performance differences are statistically significant across nearly all metrics. This research provides deeper insights into the strengths and limitations of each consensus mechanism under high-load conditions using Hardhat, and contributes to a broader understanding of blockchain scalability in real-world applications. The findings suggest that Proof of Stake is more suitable for large-scale blockchain implementations that demand high efficiency and speed.
Optimasi Penjadwalan Rapat Berbasis Web Untuk Mengurangi Konflik Jadwal Menggunakan Kombinasi Algoritma Greedy dan Decision Tree Ahmad, Tjoet Muty; Lamasitudju, Chairunnisa Ar.
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.3080

Abstract

The manual meeting scheduling process has a high potential for scheduling conflicts. These conflicts include delays in information, meeting room clashes, or meeting time clashes. These problems are caused by the absence of a system and visualization for managing meeting schedules. To streamline the scheduling process, a website-based meeting scheduling information system was developed for activities that are carried out routinely with high frequency, using a combination of two algorithms that can overcome these problems. The Greedy algorithm is used to detect conflicts, and the rule-based Decision Tree algorithm is used to provide alternative time or room suggestions when schedule conflicts occur. The results of blackbox testing and usability testing prove that the application of these algorithms makes the system more effective and provides the right workflow for this system. This research contributes to the development of an effective meeting scheduling system and integrates two algorithms as a new solution in managing the scheduling process.
Performance Comparison of Multilayer Perceptron (MLP) and Random Forest for Early Detection of Cardiovascular Disease Setiawan, Dita Widayanti; Lapatta, Nouval Trezandy; Amriana, Amriana; Nugraha, Deny Wiria; Lamasitudju, Chairunnisa Ar.
Journal of Applied Informatics and Computing Vol. 9 No. 6 (2025): December 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i6.10826

Abstract

Cardiovascular disease is a disorder of the heart and blood vessels that can lead to heart attacks, strokes, and heart failure, so early detection is essential. This study compares Multilayer Perceptron (MLP) and Random Forest for risk classification in a Kaggle dataset containing 70,000 samples with balanced targets. Pre-processing included age conversion, outlier cleaning, standardization, and feature selection based on feature importance. Both models were optimized using RandomizedSearchCV and evaluated using accuracy, precision, recall, F1-score, AUC-ROC, confusion matrix, and k-fold cross-validation. The results show that the accuracy of MLP is 73.90% and Random Forest is 74.23% with an AUC of 0.80 for both. Random Forest is more stable across all folds and performs better on the negative class, while MLP is slightly more sensitive to the positive class. Independent t-test and Mann-Whitney U tests show p>0.05, indicating that the difference in performance is not significant. The most influential features were diastolic blood pressure, age, cholesterol, and systolic blood pressure. The non-clinical Streamlit prototype demonstrated the model's potential for education and initial decision support.
Analisis Sentimen Terhadap Kinerja Awal Pemerintahan Menggunakan IndoBERT Dan SMOTE Pada Media Sosial X Ihalauw, Sahron Angelina; Trezandy Lapatta, Nouval; Wiria Nugraha, Deny; Wirdayanti; Ar Lamasitudju, Chairunnisa
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2957

Abstract

Social media platform X has become a key channel for expressing public opinion on political issues, including evaluating the early performance of the government. The first 100 days of an administration are a strategic period to assess policy direction and public perception. This study aims to apply and evaluate the IndoBERT model for sentiment analysis of Indonesian-language tweets discussing the 100-day performance of the Prabowo–Gibran administration, as well as to assess the impact of using the Synthetic Minority Oversampling Technique (SMOTE) to address data imbalance. A total of 15,027 tweets were collected through API crawling and processed through several stages: preprocessing, labeling using the InSet Lexicon, data splitting, and fine-tuning IndoBERT. Two scenarios were tested — without SMOTE and with SMOTE oversampling. The results show that both models achieved the same overall accuracy of 87%, but performance varied across sentiment classes. The model without SMOTE performed better in the positive class with 93% precision, whereas the SMOTE-applied model improved performance in the neutral class (F1-score increased from 70% to 71%; recall from 69% to 71%) and in the negative class (precision increased from 88% to 90%). Considering the balance across classes, the SMOTE-based model was selected as the final model and implemented into a Streamlit application for interactive sentiment analysis. This study expands the application of IndoBERT in the Indonesian political domain by combining the lexical InSet approach with SMOTE oversampling — a combination rarely applied in Indonesian political sentiment analysis. The findings highlight the importance of data balancing strategies in improving transformer-based model performance on imbalanced datasets. Future research is encouraged to explore alternative balancing methods, expand training data, and test other transformer variants to enhance accuracy and generalization.
Model Jaringan Syaraf Tiruan dalam Peramalan Kasus Positif Covid-19 di Indonesia Wirawan Setialaksana; Dwi Rezky Anandari Sulaiman; Shabrina Syntha Dewi; Chairunnisa Ar Lamasitudju; Nini Rahayu Ashadi; Muhammad Asriadi
Jurnal MediaTIK Volume 3 Issue 2, Mei (2020)
Publisher : Jurusan Teknik Informatika dan Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/mediatik.v3i2.1557

Abstract

Mitigation steps to control Covid-19 outbreak in Indonesia need to take. One of those step is forecasting the spread of the disease. This study compare two artificial neural network models in catching the pattern of Covid-19 positive total cases in Indonesia. Data Training used in this study is Indonesian total positive cases of Covid-19 from March 2 until May 26. The next 10 days data become data testing to show the model accuracy in predicting Covid-19 total cases. MLP shows a better prediction comparing to ELM.Three different prediction accuracy measurement is used – MAE, MAPE, and RMSE. All of them shows less value in MLP than in ELM.
Analisis Penyakit Mental Menggunakan Algoritma XGBoost Landusa, Natalia Anastasya; Ardiansyah, Rizka; Nugraha, Deny Wiria; Lamasitudju, Chairunnisa; Angreni, Dwi Shinta
Jurnal Locus Penelitian dan Pengabdian Vol. 5 No. 4 (2026): JURNAL LOCUS: Penelitian dan Pengabdian
Publisher : Riviera Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58344/locus.v5i4.5135

Abstract

Kesehatan mental merupakan bagian penting dalam kesejahteraan individu, dengan gangguan mental seperti skizofrenia, bipolar, dan depresi yang dapat memengaruhi kualitas hidup. Namun, diagnosa yang akurat untuk membedakan jenis gangguan ini seringkali menjadi tantangan karena gejala yang saling tumpang tindih. Penelitian ini bertujuan untuk mengklasifikasikan tiga jenis gangguan mental menggunakan algoritma XGBoost dan mengidentifikasi fitur penting yang berpengaruh dalam proses klasifikasi. Metode yang digunakan mencakup pengumpulan data dari dataset Kaggle yang berisi 3753 data pasien dengan 53 atribut dan 3 kelas gangguan mental. Proses pre-processing dilakukan untuk menormalkan data, yang kemudian digunakan untuk melatih model XGBoost. Hasil penelitian menunjukkan akurasi model sebesar 98,67% dengan nilai precision, recall, dan F1-score yang sangat tinggi, menunjukkan bahwa XGBoost efektif dalam mengklasifikasikan gangguan mental. Fitur utama yang berpengaruh dalam klasifikasi antara lain halusinasi, pikiran atau ucapan yang tidak teratur, dan delusi. Penelitian ini menyarankan penelitian lebih lanjut untuk pengembangan fitur dan validasi klinis model ini dalam konteks dunia medis.