Claim Missing Document
Check
Articles

Found 9 Documents
Search

Face Recognition Using Tiny Yolo V2 Algorithm as Attendance System Hafidz Sanjaya; Dony Susandi; Sandi Fajar Rodiyansyah
IJISTECH (International Journal of Information System and Technology) Vol 4, No 1 (2020): November
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v4i1.79

Abstract

Nowadays many websites use the usual online attendance system which does not pay attention to safety and comfort factors so that attendance activities still have a gap of cheating. Therefore, in this study the study of the application of face recognition systems in real-time using the Tiny Yolo V2 algorithm in the online attendance system. The study was conducted with several stages starting from collecting face images, the process of image improvement (preprocessing), face detection, face recognition, and data integration using web service. The test results of 10 students, each of whom has a face image facing forward as a dataset with 4 variations of distance, each of which performs 10 different face position scenarios. Based on the test results it can be concluded that the farther the distance of the face image with the webcam, the success rate decreases, it is shown at a distance of 0.5 meters the percentage of success reaches 97% and at a distance of 2 meters 88% where 2 faces are not detected and identified at the distance is due to wearing glasses and having rather dark skin.
PERANCANGAN ANIMASI INTERAKTIF UNTUK BAHAN AJAR MATA KULIAH BIOLOGI SEL BERBASIS DESKTOP MENGGUNAKAN ADOBE FLASH CS6 (STUDI KASUS PRODI PENDIDIKAN BIOLOGI FKIP UNIVERSITAS MAJALENGKA) Dendi Santana; Gilang Pratami; Hafidz Sanjaya
Prosiding SNST Fakultas Teknik Vol 1, No 1 (2019): PROSIDING SEMINAR NASIONAL SAINS DAN TEKNOLOGI 10 2019
Publisher : Prosiding SNST Fakultas Teknik

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (561.359 KB)

Abstract

Pada saat ini perkembangan ilmu pengetahuan dan teknologi (IPTEK) banyak diterapkan ke dalam berbagai bidang keilmuan. Salah satu penerapan ilmu teknologi yang sedang berkembang adalah dalam bidang pendidikan. Pemanfaatan gadget saat ini tidak hanya sebagai sarana untuk hiburan atau pekerjaan saja, melainkan bisa juga dimanfaatkan sebagai media pembelajaran yang bersifat interaktif. Contoh pemanfaatan teknologi sebagai media pembelajaran berupa bahan ajar interaktif ini bisa diterapkan pada mata kuliah Biologi Sel di Program Studi Pendidikan Biologi. Aplikasi media pembelajaran interaktif mata kuliah biologi sel ini dibuat menggunakan perangkat lunak Adobe Flash Professional CS6 dan bahasa pemrograman Action Script 3.0 sebagai aplikasi utama dan Adobe Photoshop CS4 sebagai aplikasi pembantu untuk membuat objek dengan Multimedia Development Life Cycle (MDLC) sebagai metode untuk mengembangkan sistem yang akan dibuat. Dengan dibangunnya aplikasi ini proses pembelajaran di Pendidikan Biologi FKIP Universitas Majalengka dapat  meningkatkan pemanfaatan teknologi dalam dunia pendidikan.Kata kunci : adobe flash, bahan ajar interaktif, biologi sel, mutimedia depelovment lice cycl
Face Recognition Using Tiny Yolo V2 Algorithm as Attendance System Hafidz Sanjaya; Dony Susandi; Sandi Fajar Rodiyansyah
IJISTECH (International Journal of Information System and Technology) Vol 4, No 1 (2020): November
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (876.463 KB) | DOI: 10.30645/ijistech.v4i1.79

Abstract

Nowadays many websites use the usual online attendance system which does not pay attention to safety and comfort factors so that attendance activities still have a gap of cheating. Therefore, in this study the study of the application of face recognition systems in real-time using the Tiny Yolo V2 algorithm in the online attendance system. The study was conducted with several stages starting from collecting face images, the process of image improvement (preprocessing), face detection, face recognition, and data integration using web service. The test results of 10 students, each of whom has a face image facing forward as a dataset with 4 variations of distance, each of which performs 10 different face position scenarios. Based on the test results it can be concluded that the farther the distance of the face image with the webcam, the success rate decreases, it is shown at a distance of 0.5 meters the percentage of success reaches 97% and at a distance of 2 meters 88% where 2 faces are not detected and identified at the distance is due to wearing glasses and having rather dark skin.
PREDIKSI JUMLAH KEJADIAN TITIK PANAS PADA LAHAN GAMBUT DI INDONESIA MENGGUNAKAN PROPHET Hafidz Sanjaya; Angga Kurniawan; Ibnu Ickwantoro; Abdul Ra'uf Alfansani; Kusrini; Dina Maulina
INFOTECH journal Vol. 9 No. 2 (2023)
Publisher : Universitas Majalengka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31949/infotech.v9i2.6073

Abstract

Indonesia merupakan salah satu negara dengan kawasan gambut terluas di dunia yang menyumbang setidaknya 47% dari luas gambut tropis dunia dan menjadi pemilik lahan gambut terbesar di Asia Tenggara. Lahan gambut di Indonesia diperkirakan memiliki luas 20,6 juta atau 10,8% dari luas daratan Indonesia dan banyak memberikan manfaat. Kebakaran lahan gambut menyebabkan deforestasi dan degradasi. Upaya pencegahan yang bisa dilakukan adalah memprediksi jumlah kejadian titik panas yang muncul pada lahan gambut di Indonesia. Data yang digunakan untuk prediksi adalah berupa data deret waktu kemunculan titik panas mulai dari tahun 2019 sampai dengan 2022 pada satelit Terra dan Aqua yang dimiliki NASA pada instrumen MODIS. Data yang diperoleh diproses menjadi jumlah kejadian titik panas per tanggal kejadian yang tercatat untuk selanjutnya dianalisa menggunakan model Prophet. Hasil pengujian menunjukkan bahwa model Prophet mampu melakukan prediksi jumlah kejadian titik panas dengan membaca tren, pola tahunan dan mingguan memberikan nilai RMSE sebesar 28.327.
Perbandingan Metode Random Forest dan KNN pada Analisis Sentimen Twitter Dwi Ahmad Dzulhijjah; Hafidz Sanjaya; Aji Said Wahyudi Hidayat; Almi Yulistia Alwanda; Ema Utami
Smart Comp :Jurnalnya Orang Pintar Komputer Vol 12, No 3 (2023): Smart Comp: Jurnalnya Orang Pintar Komputer
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/smartcomp.v12i3.5106

Abstract

Twitter menjadi salah satu platform media sosial yang sering digunakan untuk menyampaikan berbagai keresahan terhadap berbagai permasalahan yang ada termasuk dengan program-program yang dibuat oleh pemerintah. Tweets adalah salah satu layanan yang disediakan kepada penggunanya dimana tweets ini berisi ungkapan pendapat pengguna yang dapat juga dibaca oleh pengguna lain. Pada penelitian ini dilakukan perbandingan antara dua algoritma klasifikasi yaitu Support Vector Machine dan K-nearest Neighbor dari segi akurasi. Perbandingan ini tidak lain bertujuan untuk mengetahui algoritma klasifikasi mana yang dapat menghasilkan akurasi terbaik dalam mengklasifikasi analisis sentiment data twitter. Setelah dilakukan pengujian dan evaluasi didapatkan hasil akurasi dari algoritma SVM sebesar 83% dan KNN sebesar 49%. Kata Kunci: Analisis Sentimen; KNN; Support Vector Machine
ANALISIS SENTIMEN PUBLIK TERHADAP PENJUALAN IPHONE 16 DAN KEBIJAKAN TKDN DI INDONESIA Hidayat, Fajar Maula; Sanjaya, Hafidz
INFOTECH journal Vol. 11 No. 1 (2025)
Publisher : Universitas Majalengka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31949/infotech.v11i1.13159

Abstract

Kebijakan Tingkat Komponen Dalam Negeri (TKDN) terhadap produk Apple di Indonesia telah memicu berbagai opini di media sosial, terutama di platform X. Penelitian ini bertujuan untuk menganalisis sentimen publik terhadap kebijakan tersebut menggunakan metode machine learning. Data dikumpulkan melakukan teknik crawling, kemudian diproses dengan tahapan preprocessing untuk meningkatkan kualitas teks. Algoritma Random Forest diterapkan untuk mengklasifikasi opini menjadi kategori negatif, netral, dan positif. Hasil eksperimen menunjukkan bahwa model Random Forest mencapai akurasi 91%, presisi 91%, recall 91% dan f1-score 89%. Temuan ini memberikan wawasan bagi pelaku industri dan pembuat kebijakan dalam memahami persepsi masyarakat terkait kebijakan TKDN terhadap produk Apple, sehingga dapat menjadi pertimbangan dalam perumusan kebijakan selanjutnya.
FOREST FIRE LOCATION AND TIME RECOGNITION IN SOCIAL MEDIA TEXT USING XLM-ROBERTA Hafidz Sanjaya; Kusrini Kusrini; Kumara Ari Yuana; Arief Setyanto; I Made Artha Agastya; Simone Martin Marotta; José Ramón Martínez Salio
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 10 No. 4 (2025): JITK Issue May 2025
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v10i4.6194

Abstract

Forest fires have become a serious global threat, significantly impacting ecosystems, communities, and economies. Although remote sensing technology shows potential, limitations such as time delays, limited sensor coverage, and low resolution reduce its effectiveness for real-time forest fire detection. Additionally, social media can serve as a multimodal sensor, presenting multilingual text data with rapid and global coverage. However, it may encounter challenges in obtaining location and time information on forest fires due to limitations in datasets and model generalization. This study aims to develop a multilingual named entity recognition (NER) model to identify location and time entities of forest fires in social media texts such as tweets. Utilizing a transfer learning approach with the XLM-RoBERTa architecture, fine-tuning was performed using the general-purpose Nergrit corpus dataset containing 19 entities, which were relabeled into 3 main entities to detect location, date, and time entities from tweets. This approach significantly improves the model's ability to generalize to disaster domains across multiple languages and noisy social media texts. With a fine-tuning accuracy of 98.58% and a maximum validation accuracy of 96.50%, the model offers a novel capability for disaster management agencies to detect forest fires in a scalable, globally inclusive manner, enhancing disaster response and mitigation efforts.
IMPLEMENTASI SISTEM PENERIMAAN SANTRI BARU BERBASIS WEBSITE DI PONDOK PESANTREN AT-TADZKIR MAJA Sanjaya, Hafidz; Maula Hidayat, Fajar; Purnomo, Dwi
Jurnal Pengabdian Kepada Masyarakat Vol 3 No 2 (2025): JURNAL PENGABDIAN KEPADA MASYARAKAT (PENGMAS)
Publisher : Pusat Penelitian dan Pengabdian pada Masyarakat (P3M)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59820/pengmas.v3i2.346

Abstract

The At-Tadzkir Maja Islamic Boarding School faces challenges in its new student admission process, which is still conducted manually, making it inefficient and prone to administrative errors. To address this issue, a community service program was carried out by implementing a web-based student admission system. This system is designed to facilitate prospective students in registering online and assist the school administration in managing applicant data more effectively and accurately. The methods used in this program include needs analysis, system design, development, and training for school administrators on how to operate the system. The implementation results indicate that the web-based system enhances the efficiency of the student admission process, reduces paper usage, and provides easier access to information for both prospective students and school staff. With this system, At-Tadzkir Maja Islamic Boarding School is expected to improve its professionalism in managing student admissions and enhance the quality of its educational services.
PELATIHAN SISTEM PEMESANAN KAMAR HOTEL BERBASIS DIGITAL DI TWINS HOTEL SYARIAH BANDUNG Purnomo, Dwi; Cahyadi; Wiranto, Heri; Sanjaya, Hafidz
JURNAL PENGABDIAN KEPADA MASYARAKAT (ADI DHARMA) Vol 3 No 2 (2025): JURNAL PENGABDIAN KEPADA MASYARAKAT (ADI DHARMA)
Publisher : ABISATYA DINAMIKA ISWARA PUBLISHING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58268/adidharma.v3i2.178

Abstract

Twins Hotel Syariah Bandung is currently developing a digital-based service system to improve the efficiency and quality of services provided to guests. In the room reservation process, the hotel continues to face challenges such as manual data recording, errors in data management, and limitations in reporting. To address these issues, a team of lecturers from YPIB Majalengka of University initiated a training program on a digital hotel room reservation system designed to be simple yet capable of overcoming the classic limitations of manual processes. Furthermore, the need for ease of information delivery, service availability, and accessibility is crucial for the future development of the hotel's business. The activity was carried out in several stages, including system needs identification, system analysis and design, system development, preparation of training materials, implementation of the system in the hotel environment, and intensive training for relevant staff. The methods used include in-person and online training, hands-on practice with the system, and evaluation sessions to identify challenges during and after the training. The results showed an increase in staff skills in using the hotel room reservation application, a reduction in administrative errors, and improved time efficiency in serving guests. Additionally, the system is capable of generating automatic reports that assist management in decision-making. Overall, this community service activity had a positive impact and can serve as a model for the application of information technology-based community engagement that is practical and sustainable.