Bachelor Information Technology STT Pelita Bangsa, Magister Information System STMIK LIKMI,
RESEARCH INTERESTS
Information System
9
Scopus Publications
Scopus Publications
Understanding User Needs for a Mobile Health Application: Insights into Fasting, Training, and Muscle Development Lila Setiyani Journal of Applied Data Sciences, 2026 Mobile Health (mHealth) applications are increasingly used to support intermittent fasting, fitness training, and nutrition tracking. However, existing solutions remain fragmented, focusing on isolated domains without addressing users’ holistic health needs. This study aimed to explore user needs and preferences for an integrated mobile health application that combines fasting, training, and muscle development, emphasizing feature importance, usability expectations, and privacy concerns. A mixed-methods approach was used: a survey (n = 50) captured demographic profiles, feature prioritization, and usability expectations, while interviews (n = 10) explored user experiences and challenges. Quantitative data were analyzed using descriptive statistics, while qualitative interview responses were grouped into key themes through manual coding and interpretation. Results from both approaches were triangulated to strengthen the validity and reliability of findings. Users prioritized workout progression tracking (M = 4.94, SD = 0.18, 95% CI [4.89, 4.99]) and protein/macro monitoring (M = 4.20, SD = 0.42) over fasting timers (M = 2.92/5) or motivational features (M = 2.88). Usability expectations were high (Ease of Use = 6.06/7; System Capability Fit = 6.36/7), and privacy was a non-negotiable factor (M = 5.00/5). Themes revealed frustrations with incomplete exercise libraries, fragmented features, and lack of personalization. The study highlights the need for integrated, user-centered mHealth applications that unify fasting, training, and nutrition while embedding privacy-by-design principles. Future work will advance this study through prototype development and usability testing using SUS and UMUX-Lite metrics.
Implementation of YOLOv11 for Automatic Offside Detection in Football Ayu Nur Indahsari, Lila Setiyani, Devi Fajar Wati, Solikin 2025 10th International Conference on Informatics and Computing Icic 2025, 2025 Offside decisions in football often spark debates and controversies due to the rapid movement of players and the ball, as well as the limited capacity of referees to observe dynamic match situations accurately. These errors can significantly affect fairness and match outcomes. Although the Video Assistant Referee (VAR) system has been introduced to assist referees, it still relies heavily on manual interpretation, which is prone to bias and inconsistency. To address these challenges, this study presents the development of an automatic offside detection system using the YOLOv11 object detection model. Two variants-YOLOv11 Nano (YOLOv11n) and YOLOv11 Small (YOLOv11s)-are evaluated for their effectiveness in detecting offside situations. The methodology includes dataset preparation by collecting and annotating football footage, followed by model training and evaluation. Both models are assessed based on mean Average Precision (mAP@0.5 and mAP@0.5:0.95), inference speed, and robustness across different match scenarios. Experimental results show that YOLOv11n achieves higher detection accuracy, while YOLOv11s demonstrates greater stability across varied conditions. As the first study to apply YOLOv11 for automatic offside detection in football, this research highlights the novelty of integrating state-of-the-art object detection into officiating. The comparative insights between YOLOv11n and YOLOv11s provide valuable guidance for future applications of AI in sports analytics, aiming to enhance fairness, objectivity, and efficiency in referee decision-making.
DC - DRC Optimization using Load Balancer (Case Study: Karawang Regional Hospital) Lila Setiyani, Cutifa Safitri 2023 8th International Conference on Informatics and Computing Icic 2023, 2023 The development of modern applications to support company business processes requires management with high service availability. Most application development still implements traditional client server architecture, without considering the need for high availability. Karawang Regional Hospital currently still uses this traditional architecture, so data availability has the potential to experience problems. Data Center – Disaster Recovery Center (DC-DRC) is an opportunity to meet high availability needs, so the right method is needed to build a DC-DRC that has optimal performance. This research aims to increase data availability at Karawang Regional Hospital through the implementation of DC-DRC which has high availability capabilities. The load balancer method was chosen to divide the distribution of server performance loads. This research method adopts a network development process model, namely Network Development Life Cycle (NDLC) with stages including analysis, design, simulation, and implementation. Based on the test results, the applied load balancer can share the load on DC-DRC and support high availability at Karawang Regional Hospital. The results of this research can be applied to the development of DC-DRC which can be used to increase the availability of service quality.
Exploratory Data Analysis and Predict Income Udemy Course Instructors Using Machine Learning Algorithm Lila Setiyani, Nansy Herina, Yeny Rostiani Iccosite 2023 International Conference on Computer Science Information Technology and Engineering Digital Transformation Strategy in Facing the Vuca and Tuna Era, 2023 Udemy Course as an online course platform that has been recognized by both students and teachers as a medium that facilitates the transfer and receiving of knowledge, while also providing income to the Instructors. This study aims to explore datasets in Udemy Course and predict the income of the Instructors in the Udemy course. Datasets are taken from Kaggle. The research procedure begins with the collection of datasets from Kaggle, followed by datasets pre-processing, then exploratory data analysis is carried out and predicted, the implementation of machine learning random forest techniques is carried out. The results of this study show a description of the Udemy Course datasets for 2010 - 2022, course distribution prices, customer distribution, course content length distribution, number of courses for each category, number of subscribers for each category, and date of publication. In addition, this study shows that the percentage score n_estimator of machine learning random forest techniques in predicting the income of Udemy course instructors is 94%.
Comparison of the Performance of the SQL Injection Detection Model Using CNN, Logistic Regression, Random Forest, Naive Bayes, and Decision Tree Lila Setiyani, Hanny Hikmayanti Handayani, Wildan Adhitya Geraldine 2023 1st International Conference on Advanced Engineering and Technologies Iconnic 2023 Proceeding, 2023 Modern application development needs to consider security. In addition, with the increasing threat of cybercrime, software developers must be able to improve the quality of the applications they build. Machine learning has been widely implemented as a model that can increase application sophistication in detecting threats. SQL Injection ranks in the top 10 vulnerabilities in the OWASP framework. The purpose of this research is to find the best machine learning and deep learning models in detecting SQL Injection attacks. In this research, 5 algorithms will be tested, namely CNN, Logistic Regression, Random Forest, Naive Bayes, and Decision Tree. The procedure of this study adopts the AI development life cycle process with stages including project planning, data collection, data preparation, model development and model deployment. In this study, the datasets collected were unbalanced, so the process of data acquisition and preparation became important. To balance the data, the SMOTE technique is used. The results of this study indicate that CNN is the best algorithm model in detecting SQL Injection with an accuracy value of 0.95, compared to Logistic Regression 0.93, Random Forest 0.91, Naive Bayes 0.81 and Decision Tree 0.91.
Rice Price Forecasting Using GridSearchCVand LSTM Lila Setivani, Hanny Hikmayanti Handayani, Wildan Adhitya Geraldine Proceedings Icmeralda 2023 International Conference on Modeling and E Information Research Artificial Learning and Digital Applications, 2023 Forecasting supports the decision-making process. Many business decisions affect the entire line of companies or individuals. Therefore, forecasting needs to be supported by the most effective methods. Rice as a food staple is the most important part for the community and business actors. Forecasting the price of rice will certainly support the right decision making for the community or business actors. The purpose of this study is to present a rice price forecasting model that is effective in providing input to the public. This effective output will be built using LSTM supported with GridSearchCV and Sliding Window. The datasets are taken from the Central Statistics Agency which records rice price movements over a period of several years. This research procedure begins with data collection, data preparation, model development, model evaluation and deployment into rice price forecasting applications. The results of this study indicate that the deployed application can predict prices well and support the community and business actors in making decisions.
Finding the Best Techniques for Predicting Term Deposit Subscriptions (Case Study UCI Machine Learning Dataset) Lila Setiyani, Ayu Indahsari, Rosalina, Tjong Wansen Icsec 2022 4th International Conference on Sustainable Engineering and Creative Computing Proceedings, 2022 Knowing a lot about attributes, such as bank client data, marketing campaigns, social and economic context, and so on, is necessary to predict which bank customers are likely to sign up for time deposits. The direct marketing campaigns dataset for the bank institution was made available by the UCI machine learning repository. This dataset had previously been used in studies to forecast customers who would sign up for time deposits, but the outcomes of the two studies were different. The purpose of this study is to determine which machine learning methods are most effective for predicting customers who will sign up for time deposits. In this study, researchers used machine learning methods like random forests, K-nearest neighbors, decision trees, naive bayes, logistic regression, SVM, and XGBoost to uncover the truth. Results showed that XGBoost had the highest accuracy (91.73%), followed by the DT classifier (88.79%), LR classifier (91.2%), NB classifier (84.78%), KNN classifier (90.6%), SVM (89.6%), and XGBoost (91.44%).
The Impact Of Technological-Personalenvironmental (Tpe) Factors On Server-Based Electronic Money Users In Indonesia Journal of Management Information and Decision Sciences, 2021
