Yuslena Sari

Dr. Yuslena Sari

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 January 2019 in Jurnal Teknologi Informasi dan Ilmu Komputer
Verified
Journal Article
Open access
PDF file
YSYuslena Sari
Yuslena Sari
MAMuhammad Alkaff
Muhammad Alkaff
EWEka Setya Wijaya
Eka Setya Wijaya
SSSyarifah Soraya
Syarifah Soraya
DKDany Primanita Kartikasari
Dany Primanita Kartikasari
AbstrakBagi sebuah perguruan tinggi, penjadwalan perkuliahan merupakan suatu kegiatan yang sangat penting untuk dapat terlaksananya proses belajar mengajar yang baik. Dimana dalam proses belajar mengajar dapat dilakukan oleh semua pihak yang terkait, bukan hanya bagi dosen yang mengajar, tetapi juga bagi mahasiswa yang mengambil mata kuliah. Dalam penyusunan jadwal, ada beberapa variabel yang mempengaruhi yaitu: ruangan yang tersedia, jumlah mata kuliah yang diselenggarakan, waktu yang ada dan ketersediaan dosen yang mengajar. Oleh karena itu tujuan dari penelitian ini adalah merancang suatu sistem yang dapat membuat atau menyusun jadwal perkulihaan secara teroptimasi. Metode dalam proses pembuatan jadwal perkuliahan secara otomatis pada penelitian ini menggunakan metode algoritma genetika dengan teknik seleksi turnamen. hasil pengujian sistem dapat memberikan kemudahan dan kecepatan kepada user atau Program Studi Teknologi Informasi dalam proses pembuatan atau penyusunan jadwal untuk perkuliahan, yaitu hanya diperlukan waktu sekitar 14,7 menit dibandingkan dengan proses manual yang memerlukan waktu sekitar 2 (dua) hari.AbstractFor a college, the university course timetabling is is an activity that’s very important for the implementation of good teaching and learning process. In teaching and learning process can be done by all related parties, not only for Lecturers who teach, but also for students who take the course. In the preparation of the schedule, there are several variables that affect the: the available space, the number of courses held, the time available and the availability of lecturers who teach. Therefore, the purpose of this research is to design a system that can create or arrange optimization schedule optimally. Methods in the process of making university course timetabling automatically in this study using genetic algorithm method with tournament selection.

11 February 2025 in Mathematics
Verified
Journal Article
Open access
PDF file
MAMuhammad Alkaff
Muhammad Alkaff
ABAbdullah Ahmad Basuhail
Abdullah Ahmad Basuhail
YSYuslena Sari
Yuslena Sari
As global populations grow and environmental constraints intensify, improving agricultural water management is essential for sustainable food production. Traditional irrigation methods often lack adaptability, leading to inefficient water use. Reinforcement learning (RL) offers a promising solution for developing dynamic irrigation strategies that balance productivity and resource conservation. However, agricultural RL tasks are characterized by sparse actions—irrigation only when necessary—and delayed rewards realized at the end of the growing season. This study integrates RL with AquaCrop-OSPy simulations in the Gymnasium framework to develop adaptive irrigation policies for maize. We introduce a reward mechanism that penalizes incremental water usage while rewarding end-of-season yields, encouraging resource-efficient decisions. Using the Proximal Policy Optimization (PPO) algorithm, our RL-driven approach outperforms fixed-threshold irrigation strategies, reducing water use by 29% and increasing profitability by 9%. It achieves a water use efficiency of 76.76 kg/ha/mm, a 40% improvement over optimized soil moisture threshold methods. These findings highlight RL’s potential to address the challenges of sparse actions and delayed rewards in agricultural management, delivering significant environmental and economic benefits.

26 June 2018 in AIP Conference Proceedings
Verified
Conference Paper
Open access
PDF file
YSYuslena Sari
Yuslena Sari
MAMuhammad Alkaff
Muhammad Alkaff
RPRicardus Anggi Pramunendar
Ricardus Anggi Pramunendar
Iris is regarded as the most unique biometric identification. This paper proposes a new feature extraction based on iris texture patterns with Principal Component Analysis (PCA). PCA is used to store computing process in classification process. The focus of this paper was to compare the accuracy result of classification methods of distance measurement such as Euclidean Distance, City Block Distance, Chebyshev Distance, Canberra Distance and Bray-Curtis Distance. Accuracy test shows that PCA can be used in various classification methods that use distance measurement.

26 June 2018 in AIP Conference Proceedings
Verified
Conference Paper
Open access
PDF file
YSYuslena Sari
Yuslena Sari
MAMuhammad Alkaff
Muhammad Alkaff
RPRicardus Anggi Pramunendar
Ricardus Anggi Pramunendar
As an effort to preserve one of the Indonesian cultural products, this study discusses the predictions of traditional motifs. The case study is the Coastal Batik and Inland Batik. The diversity of traditional batik motifs in Indonesia began to erode due to the influx of foreign culture hence the authenticity of the traditional motifs of a particular area is not synonymous with the region of origin. As a consequent, due to many traditional Indonesian motifs, it is difficult to recognize the original motive of a particular area. It became the goal in conducting this study. Traditional motifs (Coastal Batik and Inland Batik) were data to be predicted using the method of Content-Based Image Retrieval (CBIR). With the implementation of feature extraction of Gray Level Co-Occurrence Matrices (GLCM) with a classification method using CBIR to calculate Canberra Distance, the level of accuracy of the classification results was obtained.

Verified
Journal Article
Open access
PDF file
ABAhmad Alim Bachri
Ahmad Alim Bachri
MMMutia Maulida
Mutia Maulida
YSYuslena Sari
Yuslena Sari
SSSunardi Sunardi
Sunardi Sunardi
The COVID-19 pandemic has precipitated several challenges, prompting the Indonesian government to enact rules aimed at minimizing direct contact to mitigate the spread of COVID-19, which has also affected transactional activities. Transactions conducted using a digital wallet represent a technological advancement that facilitates a cashless society lifestyle. Bank Indonesia established the Quick Response Code Indonesian Standard (QRIS) as a QR Code standard for digital payments using Electronic Money-Based (EU) servers, electronic wallets, or Mobile Banking. This study aims to identify the elements that affect consumer willingness to convert from cash payments to the QRIS during the COVID-19 epidemic. This study collected data through an online survey, distributing a 17-item questionnaire to QRIS users, yielding 568 valid responses. This research used a modified version of the Push-Pull-Mooring theory and an adaptation of the Unified Theory of Acceptance and Use of Technology (UTAUT2) model, concentrating on consumers’ intentions to transition from cash payments to QRIS utilization. This study employed the Hybrid SEM-ANN methodology with the SmartPLS and IBM SPSS Statistics 27 applications for data analysis. This investigation had 11 hypotheses, of which 4 were accepted. The findings indicated that alternative attractiveness, trust, critical mass, and traditional payment habits significantly influenced the intention to transition from cash payments to QRIS payments during the COVID-19 pandemic.

1 September 2023 in International Journal of Electronics and Telecommunications
Verified
Journal Article
Open access
PDF file
IBIda Barkiah
Ida Barkiah
YSYuslena Sari
Yuslena Sari
This study proposes a method that combines Histogram of Oriented Gradients (HOG) feature extraction and Extreme Gradient Boosting (XGBoost) classification to resolve the challenges of concrete crack monitoring. The purpose of the study is to address the common issue of overfitting in machine learning models. The research uses a dataset of 40,000 images of concrete cracks and HOG feature extraction to identify relevant patterns. Classification is performed using the ensemble method XGBoost, with a focus on optimizing its hyperparameters. This study evaluates the efficacy of XGBoost in comparison to other ensemble methods, such as Random Forest and AdaBoost. XGBoost outperforms the other algorithms in terms of accuracy, precision, recall, and F1-score, as demonstrated by the results. The proposed method obtains an accuracy of 96.95% with optimized hyperparameters, a recall of 96.10%, a precision of 97.90%, and an F1-score of 97%. By optimizing the number of trees hyperparameter, 1200 trees yield the greatest performance. The results demonstrate the efficacy of HOG-based feature extraction and XGBoost for accurate and dependable classification of concrete fractures, overcoming the overfitting issues that are typically encountered in such tasks.