Article Per Year (5 Year)
p-Index From 2021 - 2026
2.863
P-Index
This Author published in this journals
All Journal JIKO (Jurnal Informatika dan Komputer) Compiler Jiko (Jurnal Informatika dan komputer) Jurnal Manajemen Informatika bit-Tech Scientific Journal of Informatics Djtechno: Jurnal Teknologi Informasi KLIK: Kajian Ilmiah Informatika dan Komputer Journal of Creative Student Research Jurnal Abdi Rakyat
Agus Suhendar
Universitas Teknologi Yogyakarta
Religion Arts Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Languange, Linguistic, Communication & Media Social Sciences Transportation Other

Published : 18 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 18 Documents
Search

 1   2 
Classification of Hand Gestures Using Random Forest and MediaPipe in an Educational Mathematics Game M. Ridha Ansari Adriansyah; Agus Suhendar
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.3172

Abstract

Conventional mathematics learning at the elementary level often lacks interactivity, leading to low student motivation. This issue hinders the development of foundational analytical skills, despite significant time allocation in the curriculum. This research addresses this pedagogical problem by developing an educational game that replaces traditional input methods with kinesthetic interaction, aiming to directly enhance student engagement. The proposed method is a real-time hand gesture detection system built on a desktop platform. The system utilizes the MediaPipe framework to accurately extract 21 key hand landmarks from a live video feed, which serve as robust features for analysis. These features are then classified using a Random Forest algorithm, chosen for its efficiency and high performance in handling complex data, with an undersampling technique applied to ensure a balanced dataset. The performance evaluation showed that the developed classification model achieved a high accuracy of up to 98% on the test data. The resulting functional prototype allows users to answer addition and subtraction problems intuitively through hand gestures, featuring direct visual feedback and a score-tracking mechanism. This study successfully demonstrates that digital image processing can be effectively leveraged to create an engaging and adaptive mathematics learning experience. This approach not only addresses motivation in mathematics but also demonstrates the potential of gesture-based kinesthetic learning for designing a new class of engaging educational tools across various subjects, highlighting its broader impact on future educational game design.
Application of Support Vector Machine Algorithm and Image Processing in Coffee Bean Quality Classification Febi Wulan Dini; Agus Suhendar
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.3283

Abstract

This research was conducted to address the problem of the coffee bean sorting process, which is still performed manually in Empat Lawang Regency. The process is time-consuming, requires a large amount of human labor, and often results in inconsistent quality assessment. To overcome this, the study developed an automated classification system based on Support Vector Machine (SVM) utilizing Image Processing. The dataset was obtained directly from local collectors and consists of 740 coffee bean images, encompassing 286 good beans, 240 moldy beans, and 214 damaged beans. Feature extraction was performed based on three main characteristics color, size, and texture. Color features were calculated using the mean of RGB and HSV, while size features were obtained from the calculation of area, perimeter, and roundness. Texture features were extracted using the GLCM method. The SVM model was built using the RBF kernel and optimized with parameters C = 2 and gamma = 0.1. The evaluation results showed an accuracy of 94.37%, precision of 94.41%, recall of 94.37%, and an F1-score of 94.35%. The novelty of this research lies in the integration of color size texture features for the three-class classification of coffee beans using a lightweight model that is easily implementable at the MSME scale. However, the model is still limited to single-object images. Therefore, further research is suggested to include multi-bean datasets and consider deep learning methods that are more adaptive to variations in the number and position of coffee beans, such as CNN with YOLO or R-CNN.
Implementation of the KNN Algorithm for Food Recommendation System Based on Users' Nutritional Needs Silvia Mairiani Rosdilillah; Agus Suhendar
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.3449

Abstract

This study develops a web-based food recommendation system using the K-Nearest Neighbors (KNN) algorithm to provide personalized food recommendations based on users' nutritional needs and preferences. Many individuals struggle to create balanced diets due to insufficient knowledge or time, which can lead to malnutrition or obesity. To address this, the system calculates users' nutritional needs using Basal Metabolic Rate (BMR) and Total Daily Energy Expenditure (TDEE), incorporating preference filtering provided by users. The KNN algorithm then analyzes a food database to identify items that best match the users' nutritional profiles. The system features two primary interfaces: a user interface for inputting nutritional data and displaying recommendations, and an administrative interface for managing food data, user information, and recommendation history. The system was evaluated through Black Box Testing, which confirmed that all main features function as intended. The KNN algorithm demonstrated effectiveness by providing relevant food recommendations that align with users' individual nutritional requirements. Key evaluation metrics, such as recommendation accuracy and user satisfaction, validate the system's performance. This approach highlights the system’s potential in offering personalized nutrition advice, with a focus on real-time decision-making. Future work will aim to incorporate additional dietary factors and expand the food database to enhance the system’s adaptability and precision.
IMPLEMENTATION OF MSME CREDIT LOAN DETERMINATION USING MACHINE LEARNING TECHNOLOGY WITH KNN (K-NEAREST NEIGHBORS) ALGORITHM Muchamad Taufik Nawawi; Agus Suhendar
JIKO (Jurnal Informatika dan Komputer) Vol 7 No 3 (2024)
Publisher : Program Studi Teknik Informatika Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/jiko.v7i3.9064

Abstract

This research aims to develop a loan eligibility prediction model for Micro, Small, and Medium Enterprises (MSMEs) using the K-Nearest Neighbors (KNN) algorithm. The dataset utilized includes variables such as the length of business operation, number of workers, assets, and net turnover of MSMEs. The data is split into training and test sets with a 70:30 ratio. The KNN model is trained using the training data to classify loan eligibility based on a specified k value. The model predictions include whether a loan is accepted and the probability associated with each decision. The results indicate that the KNN model achieved an accuracy rate of 83.939% in predicting loan eligibility. Based on the predictions, 929 MSMEs were deemed eligible to receive loans according to the KNN model recommendations, while 170 MSMEs were classified as ineligible. These findings contribute significantly to the development of decision support systems in the banking and finance sectors, particularly in evaluating MSME loan eligibility.
Pemanfaatan Teknologi Artificial Intelligence (AI) Untuk Mendukung Kualitas Pendidikan di SMA Negeri 1 Kalibawang Murti Retnowo; Agus Suhendar; Sutarman; Farida Ardiani
Jurnal ABDI RAKYAT Vol. 1 No. 2 (2024): JURNAL ABDI RAKYAT
Publisher : Universitas Teknologi Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46923/jar.v1i2.436

Abstract

Artificial intelligence technology offers various benefits for teaching staff, which can improve the quality of teaching and the efficiency of the educational process. Artificial intelligence technology makes it very easy for teachers to prepare materials, learning methods and case studies that are relevant to the subjects taught by the teacher. An obstacle that often occurs and is faced by teachers is when teachers prepare material and deliver material using artificial intelligence (AI) technology, so it is felt necessary to hold training on the use of artificial intelligence technology, especially for teaching teachers. Through mentoring to increase teacher competency, it is hoped that teachers can be more creative and more innovative in preparing and delivering material to students. Teachers are also expected to be able to provide examples that are appropriate to the subjects taught and adapt to the current age development of students. Learning by utilizing AI technology is also expected to be able to reduce students' dependence on social media or online games which are often played by students, apart from that students are also required to read more to increase their insight in the teaching and learning process
IMPLEMENTASI ALGORITMA LONG SHORT-TERM MEMORY (LSTM) UNTUK MEMPREDIKSI HARGA BERAS DI JAWA TENGAH BERDASARKAN CUACA Yusuf Ashari; Agus Suhendar
Djtechno: Jurnal Teknologi Informasi Vol 5, No 3 (2024): Desember
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/djtechno.v5i3.5136

Abstract

Harga beras yang tidak stabil seringkali menjadi masalah bagi pemerintah dalam menjaga ketahanan pangan dan bagi petani untuk mendapatkan pendapatan yang stabil. Tujuan Penelitian untuk mengembangkan sistem prediksi harga beras di Jawa Tengah menggunakan metode Long Short-Term Memory (LSTM). LSTM dipilih karena kemampuannya dalam menangkap pola non-linear dan dependensi jangka Panjang yang terdapat dalam data time series seperti harga beras. Sistem dibangun dengan menggunakan data harga beras harian yang didapatkan dari website Pusat Informasi Harga Pangan Strategis Nasional (PIHPS Nasional) dan data cuaca harian yang diperoleh dari website BMKG di Jawa Tengah dari tahun 2017 – 2024. Arsitektur model LSTM yang digunakan terdiri dari tiga lapisan LSTM dengan dropout disetiap lapisannya dan satu lapisan Dense. Evaluasi performa model dilakukan dengan menggunakan tiga metrik evaluasi yaitu MAE, RMSE, dan MAPE. Hasil dari penelitian menunjukkan bahwa model prediksi harga beras menggunakan LSTM memiliki performa yang cukup baik berdasarkan dengan nilai metriks evaluasi, yaitu MAE sebesar 0.141, MAPE sebesar 1.256%, dan RMSE sebesar 0.205.
Pengembangan Aplikasi Pemadam Kebakaran Berbasis Smartphone Studi Kasus: Pemadam Kebakaran Yogyakarta Amallia Az Zahra; Agus Suhendar
JURNAL INFORMATIKA DAN KOMPUTER Vol 10, No 1 (2026): February 2026
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat - Universitas Teknologi Digital Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26798/jiko.v10i1.2350

Abstract

Kebakaran merupakan salah satu jenis bencana yang memiliki dampak signifikan terhadap keselamatan jiwa, kerusakan lingkungan, serta kerugian material. Tingginya jumlah kasus kebakaran di berbagai wilayah menuntut adanya sistem pelaporan yang lebih cepat, akurat, dan mudah diakses oleh masyarakat. Oleh karena itu, penelitian ini mengembangkan aplikasi pemadam kebakaran berbasis smartphone yang dirancang untuk mempercepat proses pelaporan kejadian darurat melalui tombol SOS dan pengambilan lokasi GPS secara otomatis. Aplikasi dibangun menggunakan Flutter sebagai antarmuka mobile dan Firebase sebagai backend untuk mendukung sinkronisasi data real-time antara pelapor dan petugas pemadam kebakaran. Metode penelitian mencakup observasi, wawancara, studi pustaka, perancangan sistem, implementasi antarmuka, serta pengujian black-box. Hasil penelitian menunjukkan bahwa seluruh fitur utama, termasuk registrasi, login, pelaporan darurat, GPS tracking, serta manajemen laporan pada dashboard admin, berfungsi dengan baik dan mampu menyajikan data secara real-time. Sistem yang dikembangkan terbukti dapat meningkatkan efektivitas proses pelaporan dan mempercepat respon petugas terhadap kejadian kebakaran. Dengan demikian, aplikasi FireTrack berpotensi menjadi solusi pendukung keselamatan masyarakat dalam menghadapi situasi darurat kebakaran.
Sistem Koordinasi Terintegrasi Berbasis Web dan Mobile untuk Peningkatan Pelayanan Gizi Klinis di Puskesmas Ngadirejo Maulana Rizal Alvani; Agus Suhendar
Journal of Creative Student Research Vol. 4 No. 5 (2026): Oktober: Journal of Creative Student Research
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jcsr-politama.v4i5.7160

Abstract

Coordination of clinical nutrition menus for inpatients has traditionally relied on printed sheets, handwritten notes, and instant messages, creating a high risk of miscommunication regarding patients' special dietary conditions and leaving meal service without real-time monitoring or structured historical documentation. This study designs and builds GiziCare, an integrated web and mobile coordination system for clinical nutrition menus at a primary healthcare center. The web application, built with Laravel, is used by nutritionists to manage patient data, compose a seven-day menu cycle, record special dietary notes, and monitor meal service checklists, while the Flutter-based mobile application is used by cooks to view daily menus, follow real-time checklists, and submit menu substitution requests. The two applications are integrated through a REST API and Firebase Cloud Messaging (FCM) push notifications that instantly inform cooks when a nutritionist approves or rejects a substitution request. The system was developed using the Prototype method and evaluated through Black Box Testing across 29 test scenarios covering all functional modules. The results show that all scenarios passed successfully, indicating that the system's core functions, including patient search with length-of-stay summaries, date-based menu and checklist filtering, exportable menu history, and two-way approval notifications, operate according to the defined requirements. GiziCare demonstrates that integrating web and mobile platforms through a shared API with push notifications can streamline coordination between nutritionists and cooks and reduce the miscommunication risks inherent in manual processes at primary healthcare facilities.  
Co-Authors Alvina Putri Damayani Amallia Az Zahra Elisabeth Kurnia Andini Farida Ardiani Febi Wulan Dini Fitria Ningsih Gabriel Nicolas Sumampow Ikhsan Akbar Lintang Ardi Avdillah M. Ridha Ansari Adriansyah Maulana Rizal Alvani Mawar Pratama sari Muchamad Taufik Nawawi Murti Retnowo Silvia Mairiani Rosdilillah Sutarman Visco Adam Bramasta Yusuf Ashari