cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Ramalia Noratama Putri
Contact Email
ramalia.noratamaputri@lecturer.pelitaindonesia.ac.id
Phone
-
Journal Mail Official
joisie@pelitaindonesia.ac.id
Editorial Address
-
Location
Kota pekanbaru,
Riau
INDONESIA
JOISIE (Journal Of Information Systems And Informatics Engineering)
Published by Sekolah Tinggi Ilmu Komputer Pelita Indonesia
ISSN : 25035304     EISSN : 25273116     DOI : -
Core Subject : Science,
Computer Science & IT
JURNAL JOISIE (Journal of Information System And Informatics Engineering) adalah sebuah jurnal publikasi hasil penelitian dalam bidang sistem informasi dan informatika. Jurnal JOISIE terbit secara berkala tiga kali dalam setahun yaitu bulan April, Juni, dan November.
Arjuna Subject : -
Articles 226 Documents
 19   20   21   22   23 
DUAL-LAYER ANTI-SPOOFING UNTUK SISTEM PRESENSI MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK DAN GEOFENCING HAVERSINE Yermis Duha; Gusrio Tendra; Wilda Susanti; Wahyu Joni Kurniawan; Nicholas Renaldo
JOISIE (Journal Of Information Systems And Informatics Engineering) Vol. 10 No. 1 (2026)
Publisher : Institut Bisnis dan Teknologi Pelita Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35145/joisie.v10i1.5906

Abstract

Sistem absensi berbasis web menghadapi dua vektor penipuan utama yaitu pemalsuan GPS dan pemalsuan biometrik melalui foto, video replay, atau deepfake berbasis AI. Solusi yang ada umumnya hanya mengatasi satu ancaman, meninggalkan celah keamanan yang kritis. Penelitian ini mengusulkan dan memvalidasi kerangka kerja keamanan dua lapis yang mencegah kedua ancaman secara bersamaan melalui Liveness Detection sisi klien dan geofencing sisi server. Liveness Detection menggunakan Convolutional Neural Network berbasis MobileNetV1 melalui pustaka face-api.js yang berjalan sepenuhnya di browser. Pengguna harus mempertahankan ekspresi senyum dengan probabilitas ?0,70 selama 1,5 detik sebelum absensi diaktifkan. Otentisitas lokasi diverifikasi di sisi server menggunakan Rumus Haversine dengan pengiriman melebihi radius 50 meter ditolak dengan HTTP 403. Sistem dikembangkan menggunakan metodologi Waterfall dengan backend Flask dan basis data SQLite. Evaluasi dilakukan melalui pengujian skenario keamanan terstruktur yang mengukur True Positive Rate (TPR), False Acceptance Rate (FAR), dan akurasi geofencing pada kondisi GPS stabil maupun koordinat yang dimanipulasi. Dari 40 percobaan liveness, sistem menghasilkan TPR 95%, FAR 0% terhadap serangan foto statis, dan akurasi geofencing 100% pada kondisi GPS stabil. Penelitian ini membuktikan secara nyata bahwa geofencing pada sisi klien dapat dilewati melalui Sensor Emulation browser dengan celah yang dieliminasi sepenuhnya oleh validasi sisi server. Kerangka kerja yang diusulkan memberikan ketahanan terhadap serangan presentasi dan penipuan lokasi tanpa instalasi aplikasi native. Temuan ini perlu divalidasi pada partisipan yang lebih besar, mengingat dataset terbatas pada 40 percobaan liveness dan 6 skenario geofencing. Penelitian lanjutan diprioritaskan pada ketahanan terhadap deepfake real-time dan mitigasi degradasi GPS dalam ruangan.
COMPARATIVE ANALYSIS OF MACHINE LEARNING ALGORITHMS WITH PRINCIPAL COMPONENT ANALYSIS FOR BREAST CANCER PREDICTION Lusiana Gulo; Gustientiedina Gustientiedina; Deny Jollyta; Wilda Susanti; Alyauma Hajjah
JOISIE (Journal Of Information Systems And Informatics Engineering) Vol. 10 No. 1 (2026)
Publisher : Institut Bisnis dan Teknologi Pelita Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35145/joisie.v10i1.5677

Abstract

Breast cancer is the leading cause of cancer death in Indonesia and globally, making early detection crucial. This study aims to compare the performance of Machine Learning algorithms (K-Nearest Neighbor/KNN, Support Vector Machine/SVM, Logistic Regression, Random Forest, and Decision Tree) in predicting breast cancer types using the Wisconsin Breast Cancer dataset. This dataset consists of 569 samples and is divided into training and testing sets using an 80:20 ratio. Evaluation methods include accuracy, precision, recall, F1-Score, and dimensionality reduction impact analysis using Principal Component Analysis (PCA). This study contributes by providing a comparative evaluation of several machine learning algorithms before and after PCA implementation. The results show that Random Forest achieved the highest accuracy (0.97) before PCA implementation but experienced a moderate decrease (0.94) after dimensionality reduction. KNN showed the highest consistency, maintaining a stable accuracy of 0.94 both before and after PCA. This study concludes that Random Forest is the most effective algorithm when using the full feature set, while KNN shows greater stability after dimensionality reduction, thus this study recommends KNN as a reliable solution to support accurate and efficient breast cancer diagnosis and early detection.
DESIGN AND USER EXPERIENCE EVALUATION OF MARKER-BASED AUGMENTED REALITY FOR GEOMETRY LEARNING Aulia Asyathul Hafizah; Noveri Lysbetti Marpaung; Dewi Nasien
JOISIE (Journal Of Information Systems And Informatics Engineering) Vol. 10 No. 1 (2026)
Publisher : Institut Bisnis dan Teknologi Pelita Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35145/joisie.v10i1.5990

Abstract

Three-dimensional geometry requires learners to interpret spatial relationships that are difficult to convey through static two-dimensional media. This study developed and evaluated a marker-based augmented reality (AR) application for Android to support junior-high-school geometry learning. A research-and-development approach using the waterfall software development life cycle guided requirements analysis, design, implementation, and testing. Unity 3D and Vuforia were used to present seven solids, geometric attributes, volume and surface-area formulas, nets, and three quiz levels. Product evaluation combined an adapted ISO/IEC 25010 product-quality assessment and the full User Experience Questionnaire (UEQ) with 65 respondents. Functional tests showed that registered markers generated the correct 3D objects at distances below 30 cm under adequate lighting, whereas unregistered markers produced no object. The UEQ mean scores were 2.24 for attractiveness, 2.05 for perspicuity, 2.09 for efficiency, 1.92 for dependability, 2.20 for stimulation, and 1.76 for novelty; all were classified as Excellent using the UEQ benchmark. The application demonstrated positive user experience and operational feasibility, although its effect on learning achievement was not tested.
COMPARATIVE PERFORMANCE OF MLP AND LSTM SOFT-SENSOR MODELS FOR ESTIMATING CLASS A PAN WATER LEVEL FROM HIGH-RESOLUTION AUTOMATIC WEATHER STATION DATA Asiyah Asiyah; Sajarwo Anggai; Abu Khalid Rivai; Sugiarto Sugiarto
JOISIE (Journal Of Information Systems And Informatics Engineering) Vol. 10 No. 2 (2026)
Publisher : Institut Bisnis dan Teknologi Pelita Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35145/joisie.v10i2.5997

Abstract

Evaporation is a critical meteorological parameter for hydrology, agriculture, and climatology. However, its direct observation at the Indonesian Bureau of Meteorology, Climatology, and Geophysics (BMKG) stations heavily depends on manual hook-gauge readings and automatic water-level sensors, which are highly susceptible to data gaps during equipment malfunctions. This study developed and compared two soft-sensor models, a Multi-Layer Perceptron (MLP) and a Long Short-Term Memory (LSTM) network, to estimate the 5-minute water level in a Class A evaporation pan using Automatic Weather Station (AWS) variables. One year of 5-minute-resolution data (2025) from the Fatmawati Bengkulu Meteorological Station was utilized. The model inputs included air temperature, relative humidity, wind speed, solar radiation, barometric pressure, pan water temperature, and rainfall. Based on an Autocorrelation Function analysis, the temporal lookback window was fixed at 12 lags (60 minutes). The datasets were partitioned chronologically using a 70/15/15 split for training, validation, and testing, respectively. Evaluation metrics included RMSE, MAE, and R². The MLP model achieved a lower RMSE (2.9112 mm) and a higher R² (0.9742), which may suggest a greater robustness against large prediction errors and a stronger global fit. In contrast, the LSTM model yielded the lowest MAE (1.1048 mm), indicating a lower average absolute prediction error under typical conditions, though it exhibited higher sensitivity to abrupt environmental adjustments (RMSE: 3.6215 mm). These findings indicate that both architectures represent viable soft-sensor options. Ultimately, model selection should be determined by whether the operational system prioritizes overall error stability or lower average absolute error, thereby providing practical guidance for BMKG data-continuity protocols.
PREDICTING RIDE-HAILING CUSTOMER LOYALTY USING RANDOM FOREST AND PRINCIPAL COMPONENT ANALYSIS Viola Viola; Dewi Nasien; M. Hasmil Adiya
JOISIE (Journal Of Information Systems And Informatics Engineering) Vol. 10 No. 1 (2026)
Publisher : Institut Bisnis dan Teknologi Pelita Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35145/joisie.v10i1.5998

Abstract

Customer loyalty is important for ride-hailing companies because users can easily change from one platform to another. This study applied Random Forest to classify the loyalty of ride-hailing users in Pekanbaru, Indonesia, and examined whether Principal Component Analysis (PCA) improved the result. The original dataset contained 200 questionnaire records covering demographic characteristics, trust, innovation, service quality, customer satisfaction, and customer loyalty. After seven duplicate records were removed, 193 records were divided into 154 training records and 39 test records. The baseline model achieved 0.67 accuracy and a weighted F1-score of 0.67. The best PCA model retained 80% of the variance, used seven trees, and achieved 0.69 accuracy with a weighted F1-score of 0.68. Service quality, customer satisfaction, trust, and innovation were the most important predictors. The model performed best for the Loyal class, while the smaller classes were harder to identify. One loyalty category was absent from the test set; therefore, the findings should be treated as an initial result rather than a model ready for operational use.
TALENT QUALITY MONITORING EXECUTIVE INFORMATION SYSTEM PT. SURVEYOR INDONESIAN AT JAMBI REGION WITH GENERATIVE AI INTEGRATION Fajri Arvandi; Sukma Puspitorini; Ahmad Husna Ahadi
JOISIE (Journal Of Information Systems And Informatics Engineering) Vol. 10 No. 1 (2026)
Publisher : Institut Bisnis dan Teknologi Pelita Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35145/joisie.v10i1.6072

Abstract

Surveyor Indonesia for the Jambi Province Region face obstacles in monitoring the performance and quality of talent because data management is still carried out manually using Microsoft Excel. This research aims to develop the Talent Monitoring Executive Information System (TARING-EIS) application to facilitate the monitoring and evaluation of talent competencies by the human resource (HR) department and company executives. The approach used is a case study with descriptive analysis through observation, interviews, and documentation studies. Talent competencies are assessed based on five main aspects, namely morals, leadership, experience, hard skills, and soft skills. System input data includes user data (talent and executive), internal event data, certification data, and individual ability data. The main processes in the system include talent data management, event management and certification. The system output is in the form of an interactive dashboard that displays event information, attendance, leaderboard points, and various employee performance visualizations. The system was developed using Svelte, Hono.js, and PostgreSQL, and integrates Generative AI as an internal chatbot that helps provide information related to the company and employee self-development. The results of the implementation of 20 respondents showed a user satisfaction level of 89% (4.47/5.00) based on the End User Computing Satisfaction (EUCS) test, indicating that TARING-EIS is effective and efficient in supporting the digitalization of talent management.

Page 23 of 23 | Total Record : 226

 19   20   21   22   23 

Filter by Year

2017 2026


Reset
Filter By Issues
All Issue Vol. 10 No. 2 (2026) Vol. 10 No. 1 (2026) Vol. 9 No. 2 (2025) Vol. 9 No. 1 (2025) Vol 8 No 2 (2024) Vol 8 No 1 (2024) Vol 7 No 2 (2023) Vol 7 No 1 (2023) Vol 6 No 2 (2022) Vol 6 No 1 (2022) Vol 5 No 2 (2021) Vol 5 No 1 (2021) Vol 4 No 2 (2020) Vol 4 No 1 (2020) Vol 3 No 2 (2019) Vol 3 No 1 (2019) Vol 2 No 2 (2018) Vol 2 No 1 (2018) Vol 1 No 2 (2017) Vol 1 No 1 (2017) More Issue