Claim Missing Document
Check
Articles

Found 37 Documents
Search

Video-Based Disease Detection in Vannamei Shrimp Using YOLOv8 Architecture Fathurrahman Siregar; Fadlisyah Fadlisyah; Hafizh Al Kautsar Aidilof
Brilliance: Research of Artificial Intelligence Vol. 6 No. 2 (2026): Brilliance: Research of Artificial Intelligence, Article Research May 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i2.8613

Abstract

Vannamei shrimp (Litopenaeus vannamei) is a high-value aquaculture commodity that significantly contributes to the fisheries sector. However, shrimp farming faces a high risk of disease outbreak to mass mortality and substantial economic losses. Conventional health detection methods rely on manual observation, which is subjective, inefficient, and requires expert knowledge. Therefore, this study proposes an automated shrimp health detection system based on video imagery using Convolutional Neural Networks (CNN) implemented through the YOLOv8 algorithm.The dataset consists of 2,000 images extracted from video frames of vannamei shrimp and categorized into healthy and diseased classes. The research methodology includes data preprocessing, augmentation, model training, and evaluation using performance metrics such as precision, recall, and mean Average Precision (mAP). The trained model is deployed in a web-based system using FastAPI and OpenCV to enable real-time detection. Experimental results show that the proposed CNN-based model achieves an mAP@0.5 of approximately 0.92 (92%), with precision and recall values of approximately 0.85 and 0.90, respectively. These results indicate strong detection performance under real-world conditions. The system is capable of automatically identifying shrimp health conditions and provides higher efficiency compared to manual inspection. This study demonstrates that deep learning-based computer vision has strong potential for early disease detection and can support sustainable aquaculture management
ANALISIS TREN HARGA BERAS MENGGUNAKAN ALGORITMA GATED RECURRENT UNIT Cantika Serenita; Wahyu Fuadi; Hafizh AL-Kautsar Aidilof
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.v10i2.6343

Abstract

Rice is a staple food commodity in Indonesia, including in Padang City, which is only able to meet 30% of its rice needs locally. Fluctuations in rice price affect economic stability and public purchasing power, making rice price prediction important. This study aims to develop a rice price prediction model using the Gated Recurrent Unit(GRU) method, utilizing actual historical rice price data from 2022 to April 2025 obtained from the PIPHS Nasional. The dataset includes three type of rice based on quality. Namely Bawah I, Medium I, and Super I. the result show that the GRU model provides the best model evaluation based on three types of rice, with a MAPE of 0, 49% for Medium I quality rice and an RMSE of 0,0587 for super I rice. And the highest MAPE was found in Super I quality rice, namely 4,41% , an RMSE value of 1,222 for Lower I quality rice. This model can be used to assist decision making related to rice price stability, particularly in Padang City, which relies on supplies from other regions. Overall, GRU proves effective in forecasting rice price supporting policies for more stable prices.
SISTEM INFORMASI GEOGRAFIS UNTUK PEMETAAN LOKASI MASJID DAN MEUNASAH DI KOTA LHOKSEUMAWE MENGGUNAKAN ALGORITMA HAVERSINE BERBASIS WEBSITE: GEOGRAPHIC INFORMATION SYSTEM FOR MAPPING THE LOCATION OF MOSQUES AND MEUNASAH IN LHOKSEUMAWE CITY USING THE WEBSITE-BASED HAVERSINE ALGORITHM Agus Prayoga; Fadlisyah Fadlisyah; Hafizh Al kautsar Aidilof
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.v10i2.6381

Abstract

This research aims to develop a web-based Geographic Information System (GIS) that maps the location of mosques and meunasah in Lhokseumawe City, and uses the Haversine Algorithm to calculate the closest distance between users and places of worship. The main purpose of this system is to provide fast, accurate, and efficient information, especially for newcomers or residents in finding the nearest place of worship. The method used is the waterfall system development model, with system design using the Unified Modeling Language (UML) to visualize the workflow and data structure. Data is obtained through interviews with mosque administrators and the community, as well as taking coordinates using a GPS device. The test results show that the Haversine Algorithm can calculate the distance accurately and find the location of the nearest mosque or meunasah based on the user's position. However, this system has limitations because distance calculations only consider straight lines between points (geodesic), without taking into account the actual route of the road. This research concludes that a web-based GIS that integrates the Haversine Algorithm provides real-time distance information, makes it easier for people to find the nearest place of worship, and increases the accessibility of information and participation in religious activities in Lhokseumawe City.
PENGKLASTERAN DATA KUALITAS AIR TAMBAK MENGGUNAKAN METODE GAUSSIAN MIXTURE MODEL: Statistical Approach to Identifying Pond Water Quality Patterns Assri Yani Sibuea; Asrianda Asrianda; Hafizh Al-Kautsar Aidilof
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.v10i2.6426

Abstract

This study aims to cluster pond water quality data to support decision making in fish farming management. The Gaussian Mixture Model (GMM) method is used as a probabilistic approach in clustering water quality parameters, namely pH, temperature, turbidity, and total dissolved solids (TDS). Data were collected from ponds in Kuala Kerto Village, North Aceh Regency, which is a traditional fish farming area. Before clustering, the data were cleaned from outliers and normalized using the Z-score method to improve the modeling quality. The model evaluation results showed that the GMM with 3 clusters provided the best results with a Silhouette Score of 0.55, Davies-Bouldin Index of 1.01, and the lowest BIC Score. Based on the standards for aquaculture water quality (pH 6.5–8.5, TDS <3000 mg/L, turbidity <300 NTU), each cluster was interpreted into good, moderate, and poor quality categories. Visualization of the results using PCA shows quite clear separation between clusters. This research provides a practical contribution in helping fish farmers monitor and evaluate pond water conditions in a more structured and data-driven manner.   Keywords: Gaussian Mixture Model, Pond Water Quality, Clustering, Z-Score, Silhouette Score  
IMPLEMENTASI METODE PREFERENCE SELECTION INDEX (PSI) DALAM PEREKRUTAN MITRA KURIR J&T: IMPLEMENTATION OF THE PREFERENCE SELECTION INDEX (PSI) METHOD IN RECRUITING J&T COURIER PARTNERS Alfisyahrin; Zara Yunizar; Hafizh Al Kautsar Aidilof
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.v10i2.6492

Abstract

The recruitment process for courier partners is an important aspect in maintaining the quality of delivery services in logistics companies such as J&T Express. Selecting the right candidate requires an objective and systematic method so that the decisions taken can be accounted for. This study aims to apply the Preference Selection Index (PSI) method to assist the decision-making process in the selection of courier partners. The PSI method is used to evaluate and rank prospective partners based on a number of criteria, including work experience, communication skills, problem-solving skills, discipline, and teamwork skills. This research was conducted at J&T Bireun. The analysis process was carried out through the stages of normalization, calculation of preference deviations, and determination of the final preference index value. The data used amounted to 10 employee candidates with the highest ranking results, namely Ridwan with a score of 8.6, Zikra with a score of 8.55 and Syakir with a score of 8.55. The results of the study show that the PSI method is able to provide objective and efficient selection results, and makes it easier for companies to determine the best courier partner candidates. Thus, this method is worthy of consideration as a tool in a multi-criteria-based recruitment system in the logistics industry.The courier partner recruitment process is one of the important aspects of maintaining the quality of delivery services in logistics companies such as J&T Express. The selection of appropriate candidates requires objective and systematic methods for the decision to be taken accountable. The Preference Selection Index (PSI) method to assist the decision-making process on the selection of courier partners. PSI method is used to evaluate and rank prospective partners based on a number of criteria, including work experience, communication skills, problem solving capabilities, discipline, and teamwork capabilities. This study was conducted on J&T Bireuen. The analysis process is performed through the normalization stage, preference deviation calculation, and the determination of the final preference index value. The data sample used amounted to 10 candidates with the highest ranking results, namely Ridwan with value (8.6), Zikra with value (8.55), and Syakir with value (8.55). Research results in the application of PSI methods for labor selection in the logistics sector, especially in the operational position of courier partners indicate that it is able to provide objective and efficient selection results, and facilitate the company in determining the best courier partner candidates. Thus, this method is worth considering as an alterative tool in a proof-criterion-based recruitment decision support system in the logistics industry.
Early Detection of Chili Leaf Diseases Using Convolutional Neural Network Based on Leaf Images Alam Bahari; Fadlisyah Fadlisyah; Hafizh Al Kautsar Aidilof
Brilliance: Research of Artificial Intelligence Vol. 6 No. 3 (2026): Brilliance: Research of Artificial Intelligence, Article Research August 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i3.8627

Abstract

Chili plants (Capsicum sp.) are one of the important horticultural commodities in Indonesia with high economic value. However, chili productivity is often reduced due to leaf diseases such as leaf curl, yellow leaf virus, and leaf spot disease. Manual disease identification conducted by farmers still has several limitations because it requires considerable time, experience, and is prone to observation errors. Therefore, an automatic system is needed to support early detection of chili leaf diseases quickly and accurately. This study aims to develop a chili leaf disease classification system using a Convolutional Neural Network (CNN) based on leaf images. The dataset used in this study consists of chili leaf images categorized into four classes, namely healthy leaves, leaf curl, yellow leaf, and leaf spot. The research stages include dataset collection, image preprocessing, data augmentation, CNN model training, and model evaluation using a confusion matrix with performance metrics including accuracy, precision, recall, and F1-score. The results show that the CNN model is capable of classifying chili leaf diseases with satisfactory performance. Based on the evaluation results, the model achieved a precision value of 0.75, a recall value of 0.53, and a mean Average Precision (mAP@0.5) value of 0.60. The developed system is also able to display classification results along with the confidence score of the prediction. Therefore, the CNN method has strong potential to be implemented as an image-based early detection system for chili leaf diseases to assist farmers in monitoring plant conditions more effectively.
Review AHP dalam Fenomena Gelumbung Ekonomi Asrianda Asrianda; Hafizh Al Kautsar Aidilof; Lidya Rosnita; Zulfadli Zulfadli
TECHSI - Jurnal Teknik Informatika Vol. 14 No. 1 (2023)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/techsi.v14i1.12588

Abstract

Keinginan memperoleh keuntungan didasarkan pada sifat kerakusan pada diri seseorang sehingga harga komoditas tidak akan turun dan semakin naik, kosekuensinya masyarakat berusaha untuk memiliki barang sebanyak mungkin sehingga harga naik dan mendapat keuntungan yang banyak. Mencari penyebab alasan menurun minat masyarakat terhadap barang akibat gembung ekonomi yang ada dipasaran. AHP menggabungkan pertimbangan dan penilaian pribadi dengan cara yang logis dan dipengaruhi imajinasi, pengalaman, dan pengetahuan untuk menyusun hierarki dari suatu masalah yang berdasarkan logika, intuisi dan juga pengalaman untuk memberikan pertimbangan. Dari hasil perhitungan menggunakan metode AHP dapat diambil kesimpulan bahwa minat tren gelumbung ekonimi dimasyarakat Aceh khususnya Lhokseumawe disebakan oleh nilai seni dari barang yang menjadi minat dimasyarakat. Dengan perhitungan yang tersebut sesuai dengan hasil penilaian responden yang telah peneliti lakukan menggunakan metode AHP.
ANALISIS FUNDAMENTAL DALAM MEMILIH ALTCOIN PADA CRYPTOCURRENCY DENGAN PREFERENCE SELECTION INDEX (PSI) METHOD Huan Margana Ritonga; Zara Yunizar; Hafizh Al Kautsar Aidilof
TECHSI - Jurnal Teknik Informatika Vol. 15 No. 2 (2024)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/techsi.v15i2.19000

Abstract

Cryptocurrency telah menjadi salah satu topik yang menarik perhatian di dunia keuangan dan teknologi dalam beberapa tahun terakhir. Seiring dengan popularitas Bitcoin, munculnya altcoin (alternative coins) juga menunjukkan potensi besar dalam pasar cryptocurrency. Skripsi ini bertujuan untuk menentukan opsi altcoin dengan investasi paling bagus dan memiliki potensi kenaikan paling tinggi. Metode Preference Selection Index adalah metode yang paling tepat dan di pilih untuk kasus ini karena didasari dengan beberapa preferensi aalternatif dan juga kriteria yang mendukung.Web yang dikembangkan memungkinkan pengguna untuk jauh lebih mudah memilih altcoin paling berpotensi dari beberapa opsi yang telah di pilih.
SISTEM PENDUKUNG KEPUTUSAN PEMILIHAN JURUSAN SEKOLAH PADA MAN MENGGUNAKAN METODE WASPAS Rifky Firzani Marpaung; Wahyu Fuadi; Hafizh Al Kautsar Aidilof
TECHSI - Jurnal Teknik Informatika Vol. 15 No. 1 (2024)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/techsi.v15i1.19471

Abstract

Penentuan jurusan sekolah pada Madrasah Aliyah Negeri (MAN) merupakan proses penting yang harus mempertimbangkan berbagai faktor seperti nilai akademik, minat, dan bakat siswa. Namun, penentuan jurusan sering kali masih dilakukan secara manual, sehingga kurang efisien dan memerlukan waktu yang lama. Penelitian ini bertujuan untuk merancang dan membangun Sistem Pendukung Keputusan (SPK) berbasis web yang menggunakan metode Weighted Aggregated Sum Product Assessment (WASPAS) guna membantu pihak sekolah dalam menentukan jurusan yang sesuai dengan kemampuan siswa. SPK ini menggabungkan berbagai kriteria seperti nilai raport, hasil tes akademik, serta kemampuan praktek untuk memberikan rekomendasi penjurusan yang optimal. Metode WASPAS dipilih karena kemampuannya dalam mengkombinasikan metode Weighted Sum Model (WSM) dan Weighted Product Model (WPM), yang menghasilkan perhitungan yang lebih akurat. Hasil pengujian menunjukkan bahwa sistem yang dibangun mampu memberikan rekomendasi jurusan dengan lebih cepat dan efektif dibandingkan dengan metode manual. Sistem ini diharapkan dapat membantu sekolah dalam mengelola penjurusan siswa dengan lebih efisien dan objektif.
Klasifikasi Penyakit Jantung Berbasis Data Rekam Medis Menggunakan Algoritma Local Mean K-Nearest Neighbor Alayda Zaielamy Putri; Muhammad Daud; Hafizh Al Kautsar Aidilof
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.v12i1.2026.134-143

Abstract

Penyakit jantung merupakan penyebab kematian utama di dunia dengan diagnosis dini yang penting namun sering terkendala akurasi interpretasi data rekam medis kompleks. Algoritma klasifikasi tradisional seperti K-NN memiliki kelemahan dalam menangani noise dan outliers dalam data medis. Penelitian ini bertujuan mengimplementasikan algoritma Local Mean K-Nearest Neighbor untuk mengklasifikasikan penyakit jantung berdasarkan data rekam medis dengan akurasi yang lebih baik. Dataset terdiri dari 403 observasi dengan 10 variabel meliputi jenis kelamin, umur, tekanan darah, heart rate, respiratory rate, hasil elektrokardiogram, kondisi nyeri dada, dan klasifikasi diagnosis. Metode Local Mean K-NN mengadaptasi konsep K-NN tradisional dengan pendekatan local mean calculation untuk mengatasi noise dan outliers. Tahapan penelitian mencakup preprocessing data, feature encoding, feature scaling, hyperparameter tuning, dan evaluasi menggunakan metrik accuracy, precision, recall, dan F1-score. Hasil menunjukkan algoritma Local Mean K-NN dengan nilai K optimal 11 mampu mengklasifikasikan penyakit jantung dengan accuracy 71.60%, precision 69.21%, recall 71.60%, dan F1-score 70.27%. Model menunjukkan performa sangat baik dalam mendeteksi Penyakit Jantung Koroner dengan precision 91.89% dan recall 97.14%. Analisis feature importance mengidentifikasi nyeri dada sebagai indikator terpenting (73.79%), diikuti heart rate (36.40%) dan respiratory rate (25.25%). Penelitian membuktikan efektivitas Local Mean K-NN sebagai clinical decision support tool dalam klasifikasi penyakit kardiovaskular meskipun terdapat tantangan class imbalance pada kelas minoritas.