Claim Missing Document
Check
Articles

Found 37 Documents
Search

Peramalan Jumlah Mahasiswa Baru di Universitas Malikussaleh Menggunakan Metode Double Exponential Smoothing dan Bayesian Updating Indah Chairunnisa; Muhammad Fikry; Hafizh Al Kautsar Aidilof
Jurnal Pendidikan dan Teknologi Indonesia Vol 6 No 7 (2026): JPTI - Juli 2026
Publisher : CV Infinite Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jpti.2052

Abstract

Jumlah mahasiswa baru merupakan informasi krusial bagi perguruan tinggi dalam perencanaan akademik dan strategi penerimaan. Universitas Malikussaleh mengalami fluktuasi jumlah mahasiswa baru periode 2021–2025, sehingga diperlukan metode peramalan yang akurat. Penelitian ini bertujuan meramalkan jumlah mahasiswa baru Universitas Malikussaleh tahun 2026–2030 menggunakan metode Double Exponential Smoothing (DES) Holt, serta memperbarui hasil ramalan dengan Bayesian Updating berdasarkan informasi dari kuesioner calon mahasiswa. Data historis yang digunakan adalah jumlah mahasiswa baru tahun 2021–2025. Data kuesioner diperoleh dari 205 responden siswa SMA/SMK di Kota Lhokseumawe. Analisis korelasi Pearson digunakan untuk menyeleksi indikator yang paling berpengaruh terhadap jumlah mahasiswa baru. Hasil penelitian menunjukkan bahwa metode Double Exponential Smoothing (DES) menghasilkan nilai MAPE 7,88% (kategori sangat akurat) dengan ramalan jumlah mahasiswa baru tahun 2026–2030 berturut-turut 5.626, 6.197, 6.767, 7.338, dan 7.908. Lima indikator terpilih (minat, KIP-Kuliah, reputasi, fasilitas, kemudahan informasi) menghasilkan nilai evidence 0,533. Setelah Bayesian Updating (?=0,3), diperoleh hasil posterior 5.682, 6.258, 6.834, 7.411, dan 7.986. Korelasi Pearson antara evidence dan jumlah mahasiswa baru menunjukkan hubungan sangat kuat (r=0,9271; p=0,0234). Penelitian ini membuktikan bahwa integrasi Double Exponential Smoothing (DES) dan Bayesian Updating menghasilkan peramalan yang lebih adaptif terhadap informasi terkini calon mahasiswa.
Real-Time Weapon Detection and Suspect Face Capturing System Using YOLOv8 Chairina Ulfa; Muhammad Fikry; Hafizh Al Kautsar AIdilof
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13454

Abstract

The rise of violent crimes involving sharp weapons and firearms in public spaces, including educational campuses, demands an automated real-time surveillance system to assist security personnel. This study proposes a web-based weapon detection system using YOLOv8, specifically designed to detect seven object classes: sickle, machete, axe, sword, knife, pistol, and rifle. When a weapon is detected, the system automatically captures the suspect's facial image using Haar Cascade and triggers alarm notifications, detection logs, and statistical reports. This integrated data package serves as critical digital evidence to support post-incident identification and investigation. To train the model, we constructed a dataset of 11,445 images sourced from public datasets, video frame extraction, and smartphone camera captures, which was subsequently augmented to 27,687 images to enhance model generalization. The evaluation results demonstrate strong performance with a Precision of 94.3%, Recall of 87.8%, mAP@0.5 of 93.2%, and mAP@0.5:0.95 of 60.1%. Real-time testing at distances ranging from 50 cm to 500 cm confirmed that the system reliably detects most weapon classes, particularly achieving consistent detection for sickles, machetes, and rifles across all tested ranges, while performance for smaller objects like knives and pistols showed decreased accuracy at extreme distances, indicating directions for future work. The findings confirm that the proposed system effectively detects and classifies sharp weapons and firearms in real-time while simultaneously providing visual documentation of the perpetrator, offering a practical and comprehensive security solution for campus environments.
Analisis Komparatif Deteksi Spammer Menggunakan Kombinasi Mean Shift Clustering dan Local Mean K-Nearest Neighbor pada Lalu Lintas Jaringan Komputer OK Muhammad Majid Maulana; Hafizh Al Kautsar Aidilof; Nurdin Nurdin; Muhammad Sayuti; Rizal Tjut Adek; Zara Yunizar
Jurnal Informatika dan Teknik Elektro Terapan Vol. 14 No. 3 (2026)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v14i3.10005

Abstract

Alamat IP publik pada jaringan komputer berskala besar sering kali menghadapi risiko pemblokiran oleh layanan server global akibat aktivitas lalu lintas mencurigakan yang dipicu oleh perangkat spammer. Penelitian terdahulu telah mengusulkan sistem deteksi menggunakan kombinasi K-Medoids Clustering dan Gaussian Naïve Bayes Classifier. Namun, pendekatan statistik global tersebut masih menyisakan kelemahan berupa angka deteksi melolos (False Negative) yang signifikan akibat karakteristik ketimpangan kelas (class imbalance) yang ekstrem pada lalu lintas jaringan riil. Untuk mengatasi batasan tersebut, penelitian ini menerapkan sebuah pendekatan hybrid baru dengan mengintegrasikan algoritma Mean Shift Clustering dan Local Mean K-Nearest Neighbor (LMKNN). Data lalu lintas diekstraksi dari gateway Mikrotik RouterBoard RB850Gx2 pada jaringan Wi-Fi e-UnimalNet Universitas Malikussaleh. Algoritma Mean Shift yang berbasis densitas berhasil mengisolasi karakteristik lalu lintas secara mandiri menjadi 19 klaster spasial tanpa memerlukan inisialisasi jumlah kelompok di awal. Klaster-klaster mikro kemudian dilebur menggunakan ambang batas densitas menjadi representasi binary class (Normal dan Spammer). Selanjutnya, algoritma LMKNN diterapkan untuk mengklasifikasikan data uji dengan memanfaatkan metrik rata-rata jarak lokal guna memberikan representasi yang adil bagi kelas minoritas (spammer). Hasil eksperimen menunjukkan performa klasifikasi yang luar biasa, di mana nilai hiperparameter tetangga lokal optimal pada K=3 berhasil mencatatkan nilai Akurasi, Presisi, Recall, dan F1-Score mutlak sebesar 100%. Pendekatan ini terbukti sukses memangkas angka False Negative dari 23 data pada model konvensional sebelumnya menjadi 0 data murni, menjadikannya solusi deteksi anomali yang sangat andal dan robust untuk administrator jaringan.
Water Quality Monitoring and Control System for Tilapia Cultivation Based on Internet of Things Lidya Rosnita; Muhammad Ikhwani; Hafizh Al Kautsar Aidilof; Salamah Salamah; Widia Hamsi; Haris Yunanda Rangkuti
International Journal of Engineering, Science and Information Technology Vol 4, No 4 (2024)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v4i4.566

Abstract

This research analyzes the quality of water for tilapia habitat which is a type of brackish water fish that is currently widely cultivated by pond farmers. This fish is the choice because of its flexibility regarding habitat. However, despite having flexibility in terms of habitat, each harvest of tilapia that lives in a different habitat will produce tilapia with different quantity and quality. Currently, many tilapia farmers still carry out the cultivation process using traditional methods using ponds. Kuala Kerto Village, Lapang District, North Aceh is one of the locations where many tilapia fish farmers use ponds as a habitat for this fish. Not infrequently, changes in natural conditions such as rain and floods have an impact on tilapia fish ponds in this village. Thus, crop yields are very varied, often even resulting in losses. One of the reasons for this is that there is still minimal use of technology in tilapia cultivation in this village. The design of a water quality monitoring and control system for IoT-based tilapia cultivation in this research was carried out to help the problems of tilapia pond farmers. Through this research, a tool was produced in the form of a prototype IoT device that can be used to monitor and control water quality in tilapia fish ponds. This device utilizes several sensors such as turbidity sensors, ammonia sensors, salinity sensors, pH sensors, and several other sensors as data takers which will later be transmitted and displayed via a web application. Research and development of this device uses the RD method, namely research and development.
Fundamental Analysis in Choosing Altcoins in Cryptocurrency With Preference Selection Index Method Huan Margana Ritonga; Zara Yunizar; Hafizh Al Kautsar Aidilof
International Journal of Engineering, Science and Information Technology Vol 5, No 2 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i2.848

Abstract

Cryptocurrency has become one of the most intriguing topics in finance and technology in recent years. With the growing prominence of Bitcoin, the rise of altcoins (alternative cryptocurrencies) also demonstrates significant potential within the cryptocurrency market. Altcoins, which include all cryptocurrencies other than Bitcoin, offer diverse functionalities and use cases, ranging from smart contracts to decentralized finance (DeFi) applications. This thesis identifies the altcoin options with the best investment opportunities and the highest growth potential. The study employs the Preference Selection Index (PSI) method, a multi-criteria decision-making approach that evaluates alternatives based on specific preferences and criteria. This method is particularly suitable for assessing complex investment decisions involving multiple variables, such as market capitalization, technological innovation, and utility. By applying PSI, investors can decide which altcoins will likely yield substantial returns. A web-based platform has been developed as part of this research to simplify selecting promising altcoins. This platform enables users to evaluate options based on predefined criteria, such as market trends, project objectives, and development team credibility. The accessibility of this tool empowers users—whether novice or experienced investors—to navigate the dynamic cryptocurrency market more effectively. Altcoins provide a unique opportunity for diversification in investment portfolios. Unlike Bitcoin, which is often viewed as a store of value, many altcoins are designed with specific purposes and innovative features. For instance, Ethereum introduced smart contracts that revolutionized decentralized applications, while other altcoins focus on scalability or niche markets like the Internet of Things (IoT). However, investing in altcoins also comes with challenges like high market volatility, security risks, and regulatory uncertainties. Therefore, thorough research and strategic planning are essential for minimizing risks while maximizing returns in this rapidly evolving sector.
Student Learning Style Decision-Making System Using the Multi-Attribute Utility Theory Method at SMA Negeri 1 Jangka Munawarah Munawarah; Wahyu Fuadi; Hafizh Al Kautsar Aidilof
International Journal of Engineering, Science and Information Technology Vol 5, No 2 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i2.842

Abstract

Education plays a vital role in shaping individual development and national progress. One key factor influencing learning effectiveness is students' learning styles, which determine how individuals absorb, organize, and process information. Understanding these differences is crucial for designing effective teaching methods. This research develops a Decision Support System (DSS) to determine student learning styles at SMA Negeri 1 Jangka using the Multi-Attribute Utility Theory (MAUT) method. MAUT is chosen for its ability to evaluate multiple criteria, convert them into numerical values, and systematically identify the most suitable learning approach. The alternatives in this study include Project Based Learning (PBL), Problem-Based Learning (PrBL), Inquiry-Based Learning (IBL), Discovery Learning (DL), and Contextual Teaching and Learning (CTL). The MAUT analysis considers five criteria: student activeness, material understanding, collaboration, initiative and creativity, and teacher-student communication. The research stages include literature study, data collection, system and database design, MAUT implementation, and system evaluation. The results, based on MAUT calculations, show that Inquiry-Based Learning (IBL) scores the highest at 13.611, followed by Discovery Learning (DL) at 13.018, Problem-Based Learning (PrBL) at 12.975, Contextual Teaching and Learning (CTL) at 12.929, and Project Based Learning (PBL) at 12.558. This system assists educators in designing personalized learning strategies that align with students' strengths. Leveraging data-driven analysis enhances education quality, fosters a student-centred learning environment, and improves academic performance and lifelong learning habits.
Implementasi Algoritma K-Medoid pada Clustering Sayuran Unggulan di Kabupaten Aceh Utara Rini Meiyanti; Muhammad Muaz Munauwar; Rahma Fitria; Hafizh Al Kautsar Aidilof
TEKNIKA Vol. 19 No. 1 (2025): TEKNIKA
Publisher : Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.14378546

Abstract

Klasterisasi tanaman pada kelompok tani adalah proses pengelompokan tanaman berdasarkan karakteristik tertentu, seperti jenis tanaman, musim tanam, atau lokasi geografis, dengan tujuan meningkatkan efisiensi produksi. Kelompok Tani KWT Meugah Raya masih belum mampu melebihi hasil produksi pertanian sayuran di Aceh Utara. Metode data mining dapat mengidentifikasi pola-pola menarik dalam kumpulan data, salah satunya adalah algoritma K-Medoids clustering yang mengelompokkan data berdasarkan kesamaan karakteristik. Cluster terbentuk dengan menghitung sejauh mana kedekatan antara medoid dan objek non-medoids. Data yang digunakan adalah data dari Badan Pusat Statistik (BPS) pada tahun 2021-2023 di Kabupaten Aceh Utara mengumpulkan data dari 5 kategori sayuran dan 4 variabel, meliputi luas panen, produksi, luas tanaman, dan luas penanaman baru. Melalui algoritma K-Medoids, hasil klastering sayuran unggulan menghasilkan pengelompokan potensi ke dalam 3 klaster, yaitu klaster rendah (C1), sedang (C2), dan tinggi (C3) dengan mengumpulkan macam-macam data sayuran yang ditanam oleh masyarakat setempat berupa cabai besar, kacang panjang, kangkung, terong dan tomat. Langkah berikutnya adalah Menentukan nilai titik pusat awal dengan menyusun data berdasarkan urutan dari yang terendah hingga tertinggi pada setiap data variabel, berdasarkan keseluruhan data yang tersedia. Berdasarkan hasil penelitian ini, metode K-Medoids terbukti sangat efektif dalam melakukan clustering pada data hasil panen tanaman hortikultura. Evaluasi kinerja algoritma dilakukan dengan memanfaatkan Davies-Bouldin Index (DBI) sebagai metode evaluasi, dilakukan pengukuran untuk menilai kualitas pengelompokan yang dihasilkan. Setelah proses evaluasi menggunakan DBI selesai, algoritma K-Medoids memperoleh nilai 0,5537744324187953.