Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Teika

Pembatasan Jarak Presensi Dalam Sistem Presensi Daring Menggunakan Formula Haversine Ilham, Baga Pardana; Supriadi, Fidi
TeIKa Vol 14 No 2 (2024): TeIKa: Oktober 2024
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/teika.v14i2.3723

Abstract

The transformation of the manual attendance system into an online system has been carried out by various parties, including government agencies, offices, and schools. For example, a school that has implemented an electronic-based learning management system can use the attendance form feature as a way to record students' attendance in the learning process. However, this feature is considered to have shortcomings when applied during face-to-face learning in class because absent students can still fill in from wherever they are as long as they can access the form. The existence of a radius limit is necessary to limit only students who are within the range of the class area to be able to fill out the attendance form. This research aims to design an online presence system by applying the haversine formula using the Extreme Programming method. This formula was chosen because it is suitable for calculating the distance between two coordinate points on the earth's surface assuming the earth is round. Extreme Programming is a method for building fast software systems that consists of planning, design, coding, and testing phases. Through 30 experiments, a percentage of 96.6% was obtained, which shows that the haversine formula can be applied to limit the distance in a presence system.
indonesia SYSTEMATIC LITERATURE REVIEW TENTANG PENERAPAN TEKNOLOGI BLOCKCHAIN PADA BIDANG KEUANGAN Ramadan, Zeinan; Supriadi, Fidi; Indra Junaedi, Dani
TeIKa Vol 15 No 1 (2025): TEIKA - April 2025
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Distributed ledger technology, better known as blockchain, has emerged as a promising breakthrough in supporting financial inclusion, especially for populations that are not covered by conventional financial frameworks. This paper aims to investigate the contribution of blockchain in boosting financial inclusion compared to the established financial system through a systematic literature review approach. This paper summarizes literature from leading academic databases to identify key findings on the benefits, constraints, and prospects of blockchain development in the financial sector. The analysis shows that blockchain can expand the accessibility of financial services, reduce transaction costs, and provide greater transparency and protection. However, several challenges arise such as the lack of regulatory framework, knowledge disparity, and issues of scalability and interoperability. The conclusion of this review indicates that blockchain has significant potential to boost financial inclusion, but collaborative efforts from governments, corporations, and technology innovators are needed to overcome these obstacles. This paper provides an in-depth understanding of the opportunities and challenges of blockchain implementation and recommendations for further research.
Perbandingan Model Regresi Nonlinear Polynomial, Ridge, dan Lasso untuk Prediksi Biaya Asuransi Kesehatan Berdasarkan Kerangka CRISP-DM Siti Rachmania Putri; Supriadi, Fidi; Setiadi, David
TeIKa Vol 15 No 2 (2025): Jurnal
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/3kxrvj44

Abstract

The escalating cost of healthcare necessitates accurate prediction methods for determining medical insurance premiums. This research compares the performance of three nonlinear regression models, namely Polynomial, Ridge, and Lasso, in estimating individual health insurance costs. The research process follows the CRISP-DM framework, which includes the stages of business understanding, data processing, modeling, and evaluation. The dataset used is the Medical Cost Personal Dataset from Kaggle, containing 1,338 individual data points with seven demographic and behavioral features. Six outliers in the BMI and charges features were removed using the IQR method, while categorical features were encoded with One Hot Encoding. Numerical features were transformed using second-degree Polynomial Features to capture nonlinear relationships, and then the data was split into 80% training and 20% testing. Evaluation used the Mean Squared Error (MSE) and R-squared (R²) metrics. The results indicate Ridge Regression yielded the best performance with an R² value of 0.857 and an MSE of 2.35×10⁷. This model is more stable and effective in handling multicollinearity compared to the other two models. Nevertheless, the average prediction error of approximately USD 4,800 suggests the need for increased accuracy through parameter tuning or data augmentation before being implemented in a real business environment.