Claim Missing Document
Check
Articles

Found 4 Documents
Search

PEMODELAN TOPIK SARAN MAHASISWA PADA SIMAK UNISMUH MENGGUNAKAN BERTOPIC Indriani, Lis; Irhamna Rachman, Fahrim; Yusliana Bakti, Rizki; Wahyuni, Titin
Jurnal INSYPRO (Information System and Processing) Vol 9 No 2 (2024)
Publisher : Prodi Sistem Informasi UIN Alauddin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/insypro.v9i2.51308

Abstract

This study examines the use of the BERTopic algorithm for topic modeling on student feedback data collected through the SIMAK UNISMUH. The research aims to identify and visualize thematic patterns in student feedback to improve academic services and campus facilities. This study utilizes Natural Language Processing (NLP) techniques, particularly BERTopic, which combines the advantages of Bidirectional Encoder Representations from Transformers (BERT) with clustering algorithms to produce contextually rich and easily interpretable topic representations. The research data comprises 232,430 feedback entries that were processed to remove noise and irrelevant information, resulting in 26,009 valid entries. These entries were then processed using the BERTopic algorithm, generating nine distinct topics related to various aspects of academic life, including teaching methods, campus facilities, and administrative services. The coherence score of 0.637 indicates strong internal consistency within the identified topics, while the analysis reveals key areas where the university can enhance its services. The findings from this study provide actionable insights for university administrators, enabling them to make informed decisions and improve student academic performance. Additionally, this research contributes to the field of topic modeling in educational contexts and demonstrates the effectiveness of BERTopic in processing large-scale textual data.
Sistem Deteksi Ekspresi Wajah Berbasis Convolutional Neural Network (CNN) Untuk Pengenalan Emosi Manusia Wibawa. Ar, Arya; Irhamna Rachman, Fahrim; Yusliana Bakti, Rizki; Wahyuni, Titin
Jurnal INSYPRO (Information System and Processing) Vol 9 No 2 (2024)
Publisher : Prodi Sistem Informasi UIN Alauddin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/insypro.v9i2.51360

Abstract

The development of human facial expression detection systems has become a growing research topic, particularly in efforts to create applications capable of automatically understanding and responding to human emotions. This research aims to develop and evaluate a human facial expression detection system using the Convolutional Neural Network (CNN) method. The dataset used consists of facial images with various expressions sourced from diverse origins. The data undergoes several preprocessing stages, including normalization, augmentation, and splitting into training and test sets. This study employs several CNN architectures to identify emotions such as happy, sad, angry, and scared. Testing is conducted using various parameters, including training and test data splits, as well as different CNN architectures. The results show that the CNN model can achieve over 90% accuracy on training data, with the best performance on the "Happy" emotion, achieving an f1-score of 0.93. However, there is a decrease in accuracy on validation data, with an overall average accuracy of 78%, indicating challenges in model generalization. Additionally, the "Sad" emotion has the lowest recall of 0.49, indicating the need for model improvement in classifying specific emotions. This study contributes to the development of CNN-based facial expression detection systems, but further exploration of more complex architectures, evaluation with diverse datasets, and real-time testing are needed to improve system performance.
ANALISIS DETEKSI DINI PENYAKIT JANTUNG DENGAN METODE ENSEMBLE LEARNING PADA DATA PASIEN Adrianingsih, Rizka; Irhamna Rachman, Fahrim; Yusliana Bakti, Rizki; Wahyuni, Titin
Jurnal INSYPRO (Information System and Processing) Vol 10 No 1 (2025)
Publisher : Prodi Sistem Informasi UIN Alauddin

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

Abstract

Heart disease is one of the leading causes of death, requiring early detection for prompt and accurate treatment. This study aims to develop a heart disease prediction model using ensemble learning methods, specifically the Adaptive Boosting (AdaBoost) technique. This method combines several weak models to improve the accuracy of heart disease classification based on patient data. The results show that applying the ensemble learning technique with the AdaBoost method produces a highly accurate model, especially after adding demographic features such as gender and age. The model's accuracy increased from 93.75% to 100%, with precision, recall, and F1-score reaching a perfect score of 1.00 for both classes. With these excellent results, the AdaBoost method has proven to be effective in detecting heart disease at an early stage, providing opportunities for more timely and effective medical interventions. This research is expected to make a significant contribution to the development of early heart disease detection technology and improve patient quality of life through more accurate diagnoses.
PENERAPAN ALGORITMA COSINE SIMILARITY DALAM EFEKTIFITAS PENGACAKAN SOAL UJIAN ONLINE Prima Abdiguna, Aidhil; Lukman; Yusliana Bakti, Rizki
Jurnal INSTEK (Informatika Sains dan Teknologi) Vol 10 No 2 (2025): OCTOBER
Publisher : Department of Informatics Engineering, Faculty of Science and Technology, Universitas Islam Negeri Alauddin, Makassar, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/instek.v10i2.56473

Abstract

Pengacakan soal ujian online yang efektif merupakan tantangan penting dalam memastikan keadilan dan keakuratan dalam distribusi soal. Penelitian ini bertujuan untuk mengetahui bagaimana algoritma Cosine Similarity dapat diterapkan dalam sistem pengacakan soal ujian online serta mengevaluasi efektifitasnya dalam pendistribusian soal. Metode Term Frequency-Inverse Document Frequency (TF-IDF) untuk merepresentasikan soal dalam bentuk vektor numerik sebelum dilakukan perhitungan nilai kesamaan oleh algoritma Cosine Similarity, serta metode Mean Absolute Error (MAE) dan Root Mean Squared Error (RMSE) untuk memvalidasi efektifitas hasil pengacakan. Hasil serta kesimpulan dari penelitian menunjukkan bahwa penerapan algoritma Cosine Similarity dalam sistem pengacakan soal dapat dilakukan dengan sebelumnya menerapkan tahap preprocessing data dan Term Frequency-Inverse Document Frequency serta hanya digunakan sebelum tahap pengacakan, dan efektifitas penggunaan algoritma ini dinilai efektif dikarenakan selisih rata-rata antara hasil sistem dan ideal berada dikisaran 0-1, dimana berdasarkan validasi Mean Absolute Error (MAE) sebesar 0,2514 serta Root Mean Squared Error (RMSE) sebesar 0,4704, yang menunjukkan tingkat efektivitas tinggi dalam proses pengacakan.