Claim Missing Document
Check
Articles

Found 23 Documents
Search

Assessment of Employee Using Simple Multi-Attribute Technique Exploiting Rank (SMARTER) and Behaviorally Anchor Rating Scale (BARS) Method Sulastri, Heni
JISA(Jurnal Informatika dan Sains) Vol 4, No 2 (2021): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v4i2.944

Abstract

Lecturers' active role as the spearhead of higher education has an essential role in improving higher education quality and sustainability. Therefore, assessing work behaviour is needed to measure how lecturers participate in achieving the vision and mission, quality improvement, and service guarantee to students and complementary documentation. This condition became the basis of research. They are implementing decision support systems with Simple Multi-Attribute Rating Technique Exploiting Ranges (SMARTER) and Graphic Rating Scale (GRS) to measure a lecturer's behaviour by using multiple criteria. With the SMARTER method and  Behaviorally Anchor Rating Scale (BARS). By applying the impermeable BARS method, the work behaviour assessment process results in ease and accuracy that is more in line with the employees' behaviour being assessed. With the SMARTER approach, an assessment of employee work behaviour is produced, with 90% of alternatives used. The results are Good.
Android-Based Traditional Games Julianus, Ervan; Hidayat, Eka Wahyu; Sulastri, Heni
JISA(Jurnal Informatika dan Sains) Vol 3, No 1 (2020): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v3i1.632

Abstract

The traditional Bentengan game is one of Indonesia's popular cultural heritages from the 1980s to the 1990s. Aside from being a cultural heritage, this game has benefits including for sports, training for concentration, or just for public entertainment. However, in the present where technology has become widespread, this game has begun to be almost forgotten and replaced by digital games. Therefore, we need a way to keep the game sustainable by utilizing the existence of technology, namely by changing the concept of traditional to modern. In this research the transformation process from traditional to modern games will be carried out using the ATUMICS method. The results of the transformation were developed into a 3D android game with additional online multiplayer features. Alpha test results using a black box showed that most of the application functions were running as expected, and the beta testing showed satisfactory results with an average overall rating of respondents saying 82% of digital games had the value of "VERY GOOD" and was enough to describe the actual Bentengan game.
Deteksi Stres Teks Percakapan Digital Menggunakan Model LSTM Musadad, Agni; Sulastri, Heni
Jurnal Nasional Teknologi dan Sistem Informasi Vol 12 No 1 (2026): April 2026
Publisher : Departemen Sistem Informasi, Fakultas Teknologi Informasi, Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/TEKNOSI.v12i1.2026.152-159

Abstract

Early stress detection through digital conversational text is crucial for mental health, but research in Indonesian is still limited. This study designs and evaluates a Long Short-Term Memory (LSTM)-based deep learning model to classify Indonesian text as stressful or non-stressful. The model was trained and tested using a labeled dataset of 11,000 samples. The methodology included text preprocessing, model training, and sensitivity analysis of hyperparameters such as learning rate, batch size, and number of LSTM units to find the optimal configuration. The proposed model demonstrated strong performance with an accuracy of 86.48% and a balanced F1-Score of 0.87 (non-stress) and 0.86 (stress), outperforming several previous baselines. Training curve analysis identified clear overfitting, while hyperparameter sensitivity analysis revealed that the default configuration with 64 LSTM units was suboptimal—performance improved with the use of 128 LSTM units or a batch size of 128. This study confirms the effectiveness of LSTM for stress detection in Indonesian text, while also demonstrating the need for further hyperparameter optimization and the need for more robust overfitting handling techniques.