Claim Missing Document
Check
Articles

Combination of Deep Neural Network and YuNet for Python-Based Human Lifespan Prediction Apridiansyah, Yovi; Ardiansyah, Adidi Muhammad; Wijaya, Ardi
Telematika Vol 22 No 1 (2025): Edisi Februari 2025
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v22i1.14510

Abstract

Purpose: In this research on face detection, many methods face challenges in the accuracy of age prediction due to the complexity of facial features that are influenced by factors such as lighting, expression, and image quality. Therefore, this research focuses on developing more accurate and efficient methods by utilizing Deep Neural Network (DNN) and YuNet. The purpose of this study is to develop a face recognition model in detecting and determining human age automatically using Python with the DNN method to study facial patterns in determining human age precisely and integrate the YuNet library as a lightweight face detection framework that is efficient in the identification process.Design/methodology/approach: In this study, a system was created for predicting human age using the Deep Neural Network method which functions to predict age based on facial patterns in images and the Yunet method as a facial image detector. The stages of this research start from taking pictures, installing python libraries, namely opencv, face detection process, and age detection process.Findings/result: The results of the study show that the DNN and YuNet methods have tested as many as 50 samples in the form of photos of human faces taken at a distance of half a meter, so by using the DNN and YuNet methods, researchers have succeeded in obtaining the age of the human face through the image processing process which can then obtain an accuracy level or Precission of 80% and the accuracy level of success between the prediction value and the actual value given by the system is 80%.Originality/value/state of the art: In this study, the system uses Python tools where in the face detection process using the YuNet method, this method is used because YuNet can directly detect facial features in the image and is lightweight in operation. In terms of DNN prediction, it functions as a method that can predict age based on the results of facial image detection. In this study, a dataset was also used for 50 facial samples that were tested for accuracy using the confussion matrix by looking for precission, recal, and accuracy values. 
PENGGUNAAN APPSHEET BERBASIS ANDROID ABSENSI KEHADIRAN GURU DI SEKOLAH DASAR NEGERI 65 KOTA BENGKULU WALAD; Apridiansyah, Yovi
JPMTT (Jurnal Pengabdian Masyarakat Teknologi Terbarukan) Vol. 5 No. 2 (2025): Oktober
Publisher : Lembaga Penelitian Pengabdian Masyarakat Penerbitan dan Percetakan Indonesian Scholar Khiar Wafi (LPPMPP IKHAFI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54650/jpmtt.v5i2.568

Abstract

The advancement of information technology has extended to various sectors, including education. The manual attendance system at SD Negeri 65 Kota Bengkulu has several drawbacks, such as data loss risks, inefficiency in recap processing, and limited attendance reporting. Therefore, digitalizing the attendance system is essential to enhance accuracy, efficiency, and transparency in recording teachers' and staff attendance. This study aims to develop an Android-based attendance application using AppSheet as a solution for schools to improve work discipline and streamline administrative processes. The application development is conducted as part of the Internship Program (PKL) for undergraduate students of the Computer Science Program at Universitas Muhammadiyah Bengkulu. The resulting application enables digital attendance recording, integration with reporting systems, and real-time access to attendance data. This system is expected to optimize attendance management and enhance the performance of educators. Furthermore, this research can serve as a reference for other schools considering adopting similar technology.
Implementasi Metode DevOps Approach dalam Pengembangan Sistem Pengarsipan Surat RENMIN SDM Polda Bengkulu khairullah; Apridiansyah, Yovi; Pahrizal; sungkowo, belo
Jurnal Sistem Informasi dan E-Bisnis Vol 7 No 2 (2025): Agustus
Publisher : LPPMPP Yayasan Sejahtera Bersama Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54650/jusibi.v7i2.604

Abstract

This study discusses the development of the Bengkulu Regional Police Human Resources RENMIN Letter Filing System, utilizing the DevOps approach, which integrates development and operations processes continuously. The objective is to enhance release speed, system quality, and the efficiency of digital document management. Evaluation was conducted using the User Acceptance Testing (UAT) method on 50 respondents, covering five key indicators: system functionality, ease of use, access speed, system security, and compliance with work procedures. The test results showed a high success rate, at 96%, 94%, 92%, 97%, and 95%, respectively, with an average success rate of 94.8%. These findings prove that the implementation of DevOps can provide a responsive, reliable, and user-friendly system in a police environment. Keywords— DevOps, RENMIN SDM, Document Management, Police Administration
Klasifikasi Body Mass Index Berbasis Estimasi Dimensi Tubuh melalui Pengolahan Citra Digital Juliza, Sita; Apridiansyah, Yovi
Progresif: Jurnal Ilmiah Komputer Vol 21, No 2: Agustus 2025
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v21i2.3049

Abstract

The issues of impracticality and potential errors in manual height and weight measurements have driven the development of an automated digital image-based system. This study aims to develop a measurement tool using the Canny Edge Detection method in Matlab to classify Body Mass Index (BMI) status (underweight, normal, overweight, obese) without physical contact. Testing was conducted on 40 data samples, yielding an accuracy of 99.99% for height (error 0.37%) and 99.97% for weight (error 1.25%), with a maximum measurement tolerance of ±2 cm for height and ±2 kg for weight to enhance system reliability. The classification results of nutritional status based on BMI estimation showed good performance, with a classification agreement rate of 90% of the total 40 test data, indicating that the system is sufficiently reliable and efficient in classifying BMI categories based on antropometri parameter estimates from digital images.Keywords: Body Mass Index; Image Processing; Canny Edge Detection; Matlab AbstrakPermasalahan ketidakpraktisan dan potensi kesalahan dalam pengukuran manual tinggi dan berat badan mendorong pengembangan sistem berbasis citra digital secara otomatis. Penelitian ini bertujuan membangun alat bantu pengukuran menggunakan metode Canny Edge Detection dalam Guide Matlab guna mengklasifikasikan status Body Mass Index (kurus, normal, gemuk, obesitas) tanpa kontak fisik. Pengujian dilakukan pada 40 sampel data, menghasilkan akurasi 99,99% untuk tinggi badan (error 0,37%) dan 99,97% untuk berat badan (error 1,25%), dengan toleransi maksimal pengukuran ±2 cm untuk tinggi dan ±2 kg untuk berat guna meningkatkan reliabilitas sistem. Hasil klasifikasi status gizi berdasarkan estimasi BMI menunjukan performa yang baik, dengan tingkat kecocokan hasil klasifikasi mencapai 90% dari total 40 data uji yang mengindikasikan bahwa sistem cukup andal dan efisien dalam mengklasifikasikan kategori Body Mass Index berdasarkan estimasi parameter antropometrik dari citra digital.Kata kunci: Body Mass Index; Pengolahan Citra; Edge Detection Canny; Matlab  
DETEKSI GERAK BERDASARKAN FITUR WAJAH MENGGUNAKAN METODE KANADE LUCAS TOMASI (KLT) Apridiansyah, Yovi; Marhalim; Fahmi, Nofear
Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika Vol. 19 No. 2 (2025): Jurnal Teknologi Informasi : Jurnal Keilmuan dan Aplikasi Bidang Teknik Inform
Publisher : Universitas Palangka Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47111/jti.v19i2.19848

Abstract

Research by utilizing facial recognition features related to image processing and computer vision is used to produce a system that is almost close to the human visual system in general. In image processing, the detection of the movement of the rig is carried out so as to produce detection results. A problem that often occurs in the motion detection process is that every moving object in the video will be detected as a moving object. Therefore, this study will try to detect human face objects from the video data to be detected so that the detection results will later produce the detection of face objects. Every process of observing human facial movements requires a careful pre-process stage, because it is related to the observation of very smooth movements and a very fast duration. At this stage, the detection and tracking of the facial area must always be precise so that the observation of movements made in the facial area can be accurate. The solution offered for facial motion detection is to apply the Canade Lucas Tomasi (KLT) method for tracking each feature point. The performance process of KLT in detecting faces is to track each existing face by looking at the point of facial features, after the system records the features of the face, the system will detect every facial movement in the video. So by using the KLT method, it is hoped that the system can detect facial objects in the video. The results of the study by testing as many as 30 samples of video data in the form of recordings of human motion objects succeeded in detecting facial movements with an accuracy level of 96%, Recal 88% and an accuracy level of 86%.
3D Model Bahan Ajar Pengenalan Hewan Berbasis Augmented Reality Apridiansyah, Yovi; Wibowo, Sastya Hendri; Muntahanah, Muntahanah; Apriansyah, Nugraha
Jurnal Media Infotama Vol 21 No 2 (2025): Oktober
Publisher : UNIVED Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmi.v21i2.9307

Abstract

his study aims to develop an interactive learning media based on Augmented Reality (AR) technology to support the introduction of animals to elementary school students. The learning media is designed in the form of 3D animal models that visually represent the name, habitat, and characteristics of each animal. The 3D models were developed using Blender software and implemented into the AR Web Studio platform, allowing users to scan markers using a mobile device camera and display animal objects in real-time. The research method used is Research and Development (R&D), consisting of several stages: problem formulation, data collection, media development, implementation, and system evaluation. Testing was conducted using two approaches: technical testing with the black-box method and user testing through questionnaires distributed to several elementary school teachers. The technical testing results showed that all system features, such as marker detection, 3D model display, and user interaction, functioned properly. Meanwhile, user testing revealed an average satisfaction score of 76.9%, which falls into the “Good” category. Based on these results, it can be concluded that the AR-based animal learning media is feasible to use and provides a positive contribution to increasing students’ interest and understanding of the learning material in an interactive manner.
Penerapan Metode YOLOv5 untuk Klasifikasi dan Deteksi Objek Menggunakan Video Non-Real-Time Apridiansyah, Yovi; Padli, Zeko; Reswan, Yuza; Witriyono, Harry
Jurnal PROCESSOR Vol 20 No 2 (2025): Jurnal Processor
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/processor.2025.20.2.2508

Abstract

Deteksi objek merupakan salah satu penerapan utama dari teknologi computer vision dalam bidang kecerdasan buatan. Salah satu algoritma deteksi objek yang banyak digunakan karena efisiensinya adalah YOLOv5. Penelitian ini bertujuan untuk menerapkan metode YOLOv5 dalam mendeteksi dan mengklasifikasikan objek kendaraan dan manusia pada rekaman video non-real-time di kawasan Simpang Tugu Pena Kota Bengkulu. Dataset yang digunakan merupakan video hasil dokumentasi lapangan, yang kemudian dianalisis menggunakan model YOLOv5 dengan pelatihan berbasis transfer learning. Untuk menjaga identitas objek antar-frame, sistem dikombinasikan dengan metode Kalman Filter dan SORT sebagai pelacak objek. Hasil pengujian menunjukkan bahwa model yang dibangun mampu melakukan deteksi objek dengan baik pada kondisi visual yang bervariasi, serta mencapai nilai akurasi yang tinggi berdasarkan pengukuran menggunakan matriks konfusi. Penelitian ini menunjukkan bahwa penerapan YOLOv5 efektif digunakan dalam sistem dokumentasi visual berbasis AI di lingkungan ruang publik yang dinamis.
Penerapan Qr Code Geolocation Pada Presensi Dosen Fakultas Teknik Universitas Muhammadiyah Bengkulu Rajes Andika Putra; Yovi Apridiansyah; Ardi Wijaya; RG. Guntur Alam
JCOSIS (Journal Computer Science and Information Systems) Vol. 1 No. 1 (2024): Mei
Publisher : Institute for Research and Community Service

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61567/jcosis.v1i1.177

Abstract

Tujuan : Proses presensi merupakan suatu hal yang sering dilakukan setiap orang yang bekerja baik di pemerintahan maupun swasta. Pada dasarnya proses presensi menggunakan presensi manual ada juga yang telah menggunakan finger print sehingga memudahkan dalam melakukan presensi Metode/Design/Pendekatan: Di Fakultas Teknik UM Bengkulu juga sudah menggunakan system presensi dosen menggunkan finger print, akan tetapi di masa pandemic covid-19 ini seluruh kegiatan belajar mengajar banyak yang melaksanakan secara daring, sehingga dalam penelitian ini menerapkan sistem absen dengan Qr Code dan geolocation untuk mengetahui lokasi dari dosen yang melakukan absen. Qr Code yang berarti kode yang bisa menyampaikan informasi secara cepat yang bertujuan untuk mengevaluasi kinerja dosen dalam kedisiplinan kerja Hasil/Temuan: Dari penelitian ini juga menghasilkan sistem aplikasi presensi dengan menerapan QR Code Geolocation Pada Presensi Dosen Fakultas Teknik Universitas Muhammadiyah Bengkulu, Dapat memberikan informasi hasil evaluasi kinerja dosen dengan menerapan QR Code Geolocation Pada Presensi Dosen Fakultas Teknik Universitas Muhammadiyah Bengkulu, evaluasi tersebut berupa cetak riwayat yang ada pada system, serta Meningkatkan disiplin dosen dalam kegiatan belajar dan bertanggung jawab dalam bekerja dengan adanya sistem presensi geolocation ini. Kebaharuan/Originalitas/Nilai: Dengan penelitian ini maka dapat memberikan informasi presensi dengan tingkat keberhasilan sistem berdasarkan tingkat evaluasi mencapai tingkat keberhasilan 85%. Keywords: QR, geolocatioan, presensi
Implementasi Metode Preference Selection Index Dalam Penentuan Penerimaan Beasiswa Pada SMA Negeri 2 Bengkulu Selatan Kurniawan, Andika; Yovi Apridiansyah; Yulia Darmi; Harry Witriyono
JUKOMIKA (Jurnal Ilmu Komputer dan Informatika) Vol. 6 No. 2 (2023): Desember
Publisher : LPPMPP Yayasan Sejahtera Bersama Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54650/jukomika.v6i2.495

Abstract

Scholarships are a form of assistance given to students or students in the form of funds or money that will be used to help the cost of the educational process and ease the burden on students in taking the study period, especially the cost issue, given a selective scholarship program.  This study aims to implement the Preference Selection Index (PSI) method in determining scholarship acceptance at SMA Negeri 2 South Bengkulu. This study uses a quantitative approach by using secondary data in the form of a decision matrix containing criteria for determining scholarship acceptance and data on students who have applied for scholarships in the previous year. The PSI method is used to determine the relative weight of each criterion and calculate the final score for each student. The results of this study show that the PSI method can produce objective and fair decisions in determining scholarship acceptance. In the application of the PSI method, the criterion with the highest weight is academic achievement and the criterion with the lowest weight is activeness in student organizations. The results of this study can be used as recommendations for the school in determining scholarship acceptance in the following years. It is hoped that the results of this study can help schools in selecting students who meet the criteria and deserve scholarship assistance to help with their education costs.
Sistem Pendaftaran Siswa Baru SMP Negeri 17 Lebong Berbasis Web Dengan Algoritma Sequential Searching adindo, Yogi; Apridiansyah, Yovi; Ujang Juhardi; Dedy Abdullah
JUKOMIKA (Jurnal Ilmu Komputer dan Informatika) Vol. 6 No. 2 (2023): Desember
Publisher : LPPMPP Yayasan Sejahtera Bersama Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54650/jukomika.v6i2.530

Abstract

Every year the process of accepting new students in various schools is a routine activity that must be carried out. It's just that each school applies its own way of accepting prospective new students. At SMP Negeri 17 Lebong, the registration process for new students is also still carried out independently, namely candidates come first to the school to see information and fill out forms in the school committee. The core purpose of this research is to build a new student registration system based on the website so that this website can be used to make it easier for prospective students to enroll at SMPN 17 Lebong. The results of research on the use of this system can also benefit the school in recording data on prospective new students through the website. In the development of this system using a sequential searching algorithm that functions to search for data that can facilitate the data collection process
Co-Authors Abdullah, Dedy Ade Ferdiansyani Putra adindo, Yogi Afriko Manda Jaya Afrinando Kusnandi Agustio, Faidillah Ahmad Novianto Ali Sutan Pane Andika Kurniawan Andilala Anggara, Novio Angtyas Candra Pratama Apriansyah, Nugraha AR Wallad Mahfuzi Ardi wijaya Ardiansyah, Adidi Muhammad Ardoni, Yoan Ari Purjiawan Arif Setiawan Arif Setiawan Arjun Putra Nandika Audi Muhammad Jardillah Bima Satria Yudha Cecep Saputra Daffa Putra Sadhevi Dandi Sunardi Darnita , Yulia Darnita, Yulia Darsah Wendanado Daryono, Basofi Rachmadani David Chandra David Maria Vironika, Nuri Dede Erawan Dede Erwan Dede Maulana Ibrahim Dedi Arsela Dedy Abdullah Dedy Abdullah Deo Irwan Diana Diana Diana Diana Diana Dori Mabrori Eka Sahputra Fadlikal Ilham Aditma, Afredo Fahmi, Nofear Farid Achmadi Febitri, Nora Febrina, Nanda Felix, Igor Fitriani Fitriani Giova, Giova Gunawan Gunawan Gunawan Gunawan Gunawan Gunawan Guntur Alam Harry Witriyono Harry Witriyono Hary Witriyono hidayah, agung kharisma Hidayat, Roki Hidayat, Wahid Indra Setiawan Irsyad Ahmad Fauzan Javier Rezon Gumiri Juhardi , Ujang Juhardi, Ujang Julfi Siswanto Juliza, Sita Khairullah Khairullah khairullah Kurniawan, Andika M. Dhaffa Giffari M. Gilang Ramadhan M. Sapta Firdaus Mahfuzhi, AR Walad Mahfuzi, AR. Wallad Marcelina Novi Zarti Marhalim Muhammad Agung Muhammad Aksyah Muhammad Febriansyah Muhammad Husni Rifqo Muhammad Husni Rifqo Muhammad Miatsyah muhammad rizky, muhammad Muntahanah, Muntahanah Muntahannah Mutahanah Mutahanah Novian, Arif Tri Nugraha Apriansyah Nuri David Maria Veronika Nuri David Maria Veronika Nuri David Maria Veronika Padli, Zeko Pahrizal Pahrizal, Pahrizal Pariza, Rahmat Pindo Putra Pratama Putra, Erwin Dwika Putra, Riky Ade Putri Rahma Della R.S, Penti Septian Raffles, Richard Rahmat Pariza Rajes Andika Putra Ramadhan, Redho Putra Randi Trio Ardiansyah Rasyid, Muhammad Soelaiman Rensita Delpa Ria Oktarini Ria Parina Rifqo, Muhammad Husni Rina Yuniarti, Rina Ringgo Dwika Putra Ronaldo Kontesa Rozali Toyib Sahputra, Eka Sapitri Ramadhani Sastya Hendri Wibowo Shandra Nur’aini Sonita, Anisya sungkowo, belo Thio Ragil Alfares Toyib, Rozali Ujang Juhardi ujang juhardi Veronika, Nuri David Maria WALAD Walad Mahfuzhi Walad Mahfuzi Waluyo Wijaya, Ardi Wisnu Gusti Gusti Gusti Witriyono, Harry Yoga Muhamad Aryanto Yoga Saputra Yogi adindo Yogi Bakti Husada Yudha, Bima Satria Yulia Darmi Yulia Darnita yuliadarnita yuliadarnita Yuza Reswan Zarti, Marcelina Novi