cover
Contact Name
Gunawan
Contact Email
gunawan@uho.ac.id
Phone
-
Journal Mail Official
anoatik@uho.ac.id
Editorial Address
Program Studi Ilmu Komputer Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Halu Oleo Kampus Hijau Bumi Tridharma Jalan H. E. A. Mokodompit, Anduonohu Kendari, Sulawesi Tenggara - Indonesia 93232
Location
Kota kendari,
Sulawesi tenggara
INDONESIA
AnoaTIK: Jurnal Teknologi Informasi dan Komputer
Published by Universitas Halu Oleo
ISSN : -     EISSN : 29877652     DOI : https://doi.org/10.33772/anoatik
Core Subject : Science,
AnoaTIK: Jurnal Teknologi Informasi dan Komputer (eISSN 2987-7652) merupakan salah satu jurnal yang dikelola oleh program studi Ilmu Komputer pada Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Halu Oleo. Terbit 2 (dua) kali dalam setahun pada bulan Juni dan Desember sebagai salah satu wadah publikasi ilmiah pada bidang teknologi informasi dan ilmu komputer berbahasa Indonesia.
Articles 45 Documents
SISTEM PAKAR DIAGNOSA PENYAKIT HEWAN TERNAK SAPI MENGGUNAKAN METODE FORWARD CHAINING Milda Wati; Laode Saidi; Ferdinand Murni Hamundu
AnoaTIK: Jurnal Teknologi Informasi dan Komputer Vol 3 No 2 (2025): Desember 2025
Publisher : Program Studi Ilmu Komputer FMIPA-UHO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33772/anoatik.v3i2.125

Abstract

Sistem pakar bertujuan agar komputer mampu memberikan solusi cerdas seperti manusia. Salah satu algoritma yang digunakan adalah forward chaining. Berdasarkan wawancara dengan dokter hewan, jumlah dokter hewan di Kota Kendari masih sangat kurang, sehingga diagnosa penyakit ternak terkendala. Penelitian ini bertujuan menghasilkan sistem pakar untuk mendiagnosa penyakit sapi menggunakan metode Forward Chaining. Metode forward chaining merupakan metode runut maju, yang berarti menggunakan kondisi aksi. Metode ini akan menggunakan data dalam menentukan aturan mana yang akan dijalankan, setelahnya aturan tersebut akan dijalankan. Forward chaining dapat disebut sebagai metode intervensi yang dimana melakukan penalaran pada suatu masalah kepada solusinya. Metode ini sendiri menggunakan pendekatan goal-driven, diawali dengan hipotesis yang dilanjutkan dengan mencari bukti pendukung dari hipotesis tersebut Hasil uji blackbox menunjukkan seluruh fungsi sistem berjalan baik. Uji confusion matrix menunjukkan akurasi 87.5%, presisi 100%, dan recall 87.5%. Nilai akurasi dari yang kurang begitu baik dari sistem disebabkan oleh faktor keterbatasan intervensi yang dilakukan oleh sistem. Meskipun begitu sistem telah mampu digunakan secara luas dan diharapkan dapat membantu dalam proses diagnosa penyakit pada hewan ternak sapi.
ANALISIS KOMPARASI KESTABILAN ALGORITMA DECISION TREE DAN RANDOM FOREST UNTUK KLASIFIKASI GANGGUAN TIDUR Almunajat Amirul Soleh; Gusti Arviana Rahman
AnoaTIK: Jurnal Teknologi Informasi dan Komputer Vol 3 No 2 (2025): Desember 2025
Publisher : Program Studi Ilmu Komputer FMIPA-UHO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33772/anoatik.v3i2.126

Abstract

Sleep disorders are serious health conditions that are closely associated with an increased risk of hypertension and cardiovascular disease. Considering the high cost of conventional clinical diagnostic procedures, data mining techniques for early detection offer an effective alternative. This study aims to conduct a comparative performance analysis between the Decision Tree (C4.5) and Random Forest algorithms in classifying sleep disorders (None, Insomnia, and Sleep Apnea). To address class imbalance issues, this research utilizes the secondary Sleep Health and Lifestyle dataset. To evaluate model stability, a rigorous validation method, Stratified 10-Fold Cross-Validation, is employed. The experimental results indicate that the Random Forest algorithm outperforms the Decision Tree, achieving an average accuracy of 91.41% and a Kappa value of 0.8473. The primary advantage of the Random Forest algorithm lies in its ability to significantly improve the detection sensitivity of the Insomnia class to 88.31%. Based on feature importance analysis, diastolic blood pressure and the BMI category (Overweight) are identified as the most influential features in the diagnostic process. Random Forest is therefore considered a more accurate and stable model for medical decision support systems.
ANALISIS DAN IMPLEMENTASI SISTEM KONTROL LAMPU RUMAH OTOMATIS MENGGUNAKAN METODE FUZZY LOGIC I Made Alit Dwi Saputra; Ilham Julian Efendi; Subardin
AnoaTIK: Jurnal Teknologi Informasi dan Komputer Vol 3 No 2 (2025): Desember 2025
Publisher : Program Studi Ilmu Komputer FMIPA-UHO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33772/anoatik.v3i2.128

Abstract

Efficient use of electrical energy is one of the important aspects in a smart home system. One solution is an automatic lighting control system that can turn lights on or off based on environmental conditions. This study aims to design and implement an automatic home lighting control system using the Mamdani fuzzy logic inference method, with the integration of the Internet of Things (IoT) through the Blynk application for remote monitoring and control. This system usesanLDR sensor to detect environmental lighting levels and a PIR sensor to detect human movement. Data from the sensors is processed using predetermined rule-based fuzzy logic to produce lighting control decisions (ON or OFF). The implementation offuzzy logic is carried out on an Arduino microcontroller, while IoT connectivity and user interface are handled by the ESP8266 module connected to the Blynk platform. The test results show that the system can work automatically with responsiveness and accuracy. The lights turn on only when the light is dim/dark and there is movement, and can be controlled manually through the Blynk application. This system also allows monitoring ofsensor values (LDR and PIR) in real time via mobile devices. With the integration offuzzy logic and IoT, the system is proven to be effective in improving energy efficiency and user comfort in the home environment
PENGARUH PENGGUNAAN GITHUB DAN EDUTRACK TERHADAP MOTIVASI MAHASISWA DALAM PROYEK PERANGKAT LUNAK Muhammad Riansyah Tohamba; LM Bahtiar Aksara
AnoaTIK: Jurnal Teknologi Informasi dan Komputer Vol 3 No 2 (2025): Desember 2025
Publisher : Program Studi Ilmu Komputer FMIPA-UHO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33772/anoatik.v3i2.129

Abstract

The integration of digital technologies in education continues to advance, including the use of GitHub as a collaboration platform and EduTrack as a progress monitoring tool. This study aims to evaluate the impact of GitHub and EduTrack on students’ motivation during software project development. A total of 104 students participated in this study, utilizing GitHub for team project management and EduTrack for periodic progress evaluation. Data were collected through a Likert-scale questionnaire designed to measure autonomy, competence, relatedness, and industry readiness. Statistical analysis using the t-test revealed that several dimensions of students’ motivation were significantly influenced by the use of these platforms. The findings provide new insights into the integration of digital tools to support collaborative learning and prepare students for industry challenges.
PERBANDINGAN METODE CERTAINTY FACTOR DAN DEMPSTER SHAFER DALAM MENDIAGNOSIS PENYAKIT DIABETES MELLITUS PADA RUMAH SAKIT UMUM DAERAH KOTA KENDARI Wasda Bil Husna; Herdi Budiman; La Surimi
AnoaTIK: Jurnal Teknologi Informasi dan Komputer Vol 3 No 2 (2025): Desember 2025
Publisher : Program Studi Ilmu Komputer FMIPA-UHO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33772/anoatik.v3i2.130

Abstract

Diabetes Mellitus is a chronic disease that requires early and accurate diagnosis. This study aims to develop an expert system to diagnose Type 2 Diabetes Mellitus by comparing Certainty Factor and Dempster-Shafer methods. The system was developed using rule-based reasoning with symptom data and expert confidence values. Evaluation using a confusion matrix shows that the Certainty Factor method achieved higher accuracy than the Dempster-Shafer method.