Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal RABIT: Jurnal Teknologi dan Sistem Informasi Univrab
Ar Razi
Malikussaleh University
Computer Science & IT Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
SISTEM PAKAR DIAGNOSA PENYAKIT TANAMAN PEPAYA BERBASIS FUZZY LOGIC MAMDANI: PENDEKATAN EFISIEN UNTUK IDENTIFIKASI DINI: IMPLEMENTATION OF THE MAMDANI FUZZY ALGORITHM TO SUPPORT DISEASE DIAGNOSIS DECISIONS IN PAPAYA BASED ON AN EXPERT SYSTEM Arifinal; Wahyu Fuadi; Ar Razi
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 10 No 2 (2025): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v10i2.6433

Abstract

Papaya is one of the most widely cultivated horticultural commodities in Indonesia. However, this plant is susceptible to various diseases that can reduce productivity and fruit quality. Limited knowledge among farmers in identifying early disease symptoms is a major factor in failed disease management. This research aims to develop an expert system using the Mamdani Fuzzy Logic method to assist in determining types of diseases in papaya plants. The system utilizes fuzzy inference techniques capable of handling uncertain and linguistic data, and is built using the Python programming language and MySQL database. Diagnosis is performed based on symptoms entered by users, processed through fuzzification, inference, and defuzzification stages to produce the most probable disease type and its certainty level. The test results show that the system provides accurate diagnoses that align with manual expert analysis using predefined fuzzy rules. Therefore, the expert system serves as an effective solution for supporting fast and accurate identification of diseases in papaya plants.
IMPLEMENTASI CONTENT-BASED FILTERING DENGAN TF-IDF DAN COSINE SIMILARITY UNTUK SISTEM REKOMENDASI DESTINASI WISATA DI ACEH TENGAH: IMPLEMENTATION OF CONTENT-BASED FILTERING USING TF-IDF AND COSINE SIMILARITY FOR A TOURIST DESTINATION RECOMMENDATION SYSTEM IN CENTRAL ACEH Sara Oyadila; Dahlan Abdullah; Ar Razi
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 10 No 2 (2025): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v10i2.6532

Abstract

Central Aceh Regency possesses rich tourism potential, yet information about tourist destinations is often unstructured, making it difficult for travelers to choose locations that suit their preferences. This study aims to develop a tourism recommendation system based on Content-Based Filtering using TF-IDF and Cosine Similarity approaches. The system allows users to select up to five tourism-related attributes such as “culinary,” “picnic,” or “hiking” to receive destination recommendations with the highest similarity scores. The development process includes data collection from the Central Aceh Tourism Office, data preprocessing, term weighting using TF-IDF, and similarity calculation using cosine similarity. The implemented system successfully recommends three tourist destinations that best match user preferences. System testing using the black box method showed valid and expected results. The system achieved an accuracy rate of 85% during user testing, with a precision of 83% and recall of 81%, outperforming similar studies [14]. This study demonstrates that the Content-Based Filtering method is effective in delivering personalized and relevant tourism recommendations while supporting local tourism promotion efforts.
PERBANDINGAN METODE LOGISTIC REGRESSION DAN RANDOM FOREST DALAM KLASIFIKASI PENYAKIT KULIT MULTIKELAS: COMPARISON OF LOGISTIC REGRESSION AND RANDOM FOREST METHODS IN MULTICLASS SKIN DISEASE CLASSIFICATION Syatriani Jauhari; Rozzi Kesuma Dinata; Ar Razi
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 10 No 2 (2025): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v10i2.6551

Abstract

This study compares two classification algorithms, namely Logistic Regression and Random Forest, in classifying eight types of skin diseases based on ten clinical symptoms. The data used consists of 271 patient medical records from Cut Meutia General Hospital, which are divided into 80% training data and 20% test data. The pre-processing stage included imputing missing data, encoding categorical variables, and normalizing numerical features for the Logistic Regression model. Both algorithms were implemented using the Scikit-learn library in the Python programming language. Evaluation was conducted using accuracy, precision, recall, and F1-score metrics. The results show that Logistic Regression achieved an accuracy of 94.55%, slightly higher than Random Forest, which reached 92.73%. Validation using 5-fold cross-validation and a paired t-test yielded a p-value of 0.0371, indicating that the performance difference between the two models is statistically significant. However, limitations such as the relatively small amount of data and class imbalance impacted the low performance of the model in minority categories such as Psoriasis. This study is expected to serve as a foundation for the development of data-based medical diagnosis assistance systems to improve efficiency and accuracy in healthcare services.
Co-Authors Arifinal Dahlan Abdullah Rozzi Kesuma Dinata Sara Oyadila Syatriani Jauhari Wahyu Fuadi