Article Per Year (5 Year)
p-Index From 2021 - 2026
1.456
P-Index
This Author published in this journals
All Journal Rekursif: Jurnal Informatika Jurnal Promkes: The Indonesian Journal of Health Promotion and Health Education Jurnal Komunikasi Ikatan Sarjana Komunikasi Indonesia Jurnal Bina Praja Angkasa: Jurnal Ilmiah Bidang Teknologi Jurnal Sosial Ekonomi Pekerjaan Umum Jurnal Transformasi Administrasi eProceedings of Engineering
Heru Syah Putra
Telkom University
Humanities Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Social Sciences

Published : 17 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 17 Documents
Search

 1   2 
Aplikasi Pengenalan Wajah Pada Presensi Perkuliahan Menggunakan Facenet Rafieldo, Ricky Marcelino; Usman, Uke Kurniawan; Putra, Heru Syah
eProceedings of Engineering Vol. 12 No. 3 (2025): Juni 2025
Publisher : eProceedings of Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Sistem presensi mahasiswa yang masihmenggunakan metode manual atau semi-manual seringkalirentan terhadap kesalahan pencatatan dan penyalahgunaanyang dapat menggangu proses evaluasi akademik. Teknologipengenalan wajah dapat menjadi solusi dengan memungkinkanproses identifikasi individu secara unik berdasarkankarakteristik fitur wajah dan pencatatan presensi secaraotomatis dan real-time. Penelitian ini bertujuan untukmengembangkan sistem presensi pengenalan wajahmenggunakan Google ML Kit dan Facenet pada aplikasimobile. Pengujian dilakukan dengan variasi jarak,pencahayaan, dan pengunaan aksesoris untuk mengujikehandalan sistem dalam kondisi nyata. Hasil pengujianmenunjukkan akurasi 100% pada jarak 50 cm, 100 cm, dan 150cm, meskipun waktu pengenalan meningkat menjadi lambatdari 1,328 detik pada jarak 50 cm menjadi 1,963 detik padajarak 150 cm. Akurasi menurun dalam kondisi cahaya gelap,dan penggunaan aksesoris secara bersamaan seperti topi dankacamata dapat mengurangi akurasi hingga 78,75%. Selain itu,sistem memiliki False Acceptance Rate (FAR) sebesar 10% saatmengujji wajah di luar database. Secara umum, sistempengenalan wajah yang dikembangkan mampu memberikanakurasi tinggi dalam kondisi ideal, namun masih memerlukanoptimasi untuk kondisi lingkungan yang bervariasi.Kata kunci— Sistem Presensi, Pengenalan Wajah, GoogleML Kit, Facenet, Akurasi
Aplikasi Pengenalan Wajah Pada Presensi Perkuliahan Menggunakan Facenet Rafieldo, Ricky Marcelino; Usman, Uke Kurniawan; Putra, Heru Syah
eProceedings of Engineering Vol. 12 No. 3 (2025): Juni 2025
Publisher : eProceedings of Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Sistem presensi mahasiswa yang masihmenggunakan metode manual atau semi-manual seringkalirentan terhadap kesalahan pencatatan dan penyalahgunaanyang dapat menggangu proses evaluasi akademik. Teknologipengenalan wajah dapat menjadi solusi dengan memungkinkanproses identifikasi individu secara unik berdasarkankarakteristik fitur wajah dan pencatatan presensi secaraotomatis dan real-time. Penelitian ini bertujuan untukmengembangkan sistem presensi pengenalan wajahmenggunakan Google ML Kit dan Facenet pada aplikasimobile. Pengujian dilakukan dengan variasi jarak,pencahayaan, dan pengunaan aksesoris untuk mengujikehandalan sistem dalam kondisi nyata. Hasil pengujianmenunjukkan akurasi 100% pada jarak 50 cm, 100 cm, dan 150cm, meskipun waktu pengenalan meningkat menjadi lambatdari 1,328 detik pada jarak 50 cm menjadi 1,963 detik padajarak 150 cm. Akurasi menurun dalam kondisi cahaya gelap,dan penggunaan aksesoris secara bersamaan seperti topi dankacamata dapat mengurangi akurasi hingga 78,75%. Selain itu,sistem memiliki False Acceptance Rate (FAR) sebesar 10% saatmengujji wajah di luar database. Secara umum, sistempengenalan wajah yang dikembangkan mampu memberikanakurasi tinggi dalam kondisi ideal, namun masih memerlukanoptimasi untuk kondisi lingkungan yang bervariasi. Kata kunci— Sistem Presensi, Pengenalan Wajah, GoogleML Kit, Facenet, Akurasi
Analisis Performa Aplikasi Pengenalan Wajah Fast : Latensi Dan Penggunaan Sumber Daya Rizqi , Mochamad Ilman Yassir; Usman, Uke Kurniawan; Putra, Heru Syah
eProceedings of Engineering Vol. 12 No. 3 (2025): Juni 2025
Publisher : eProceedings of Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Sistem presensi konvesional masih mengalamimasalah efisiensi dalam pengelolaan kehadiran. Studi inimerancang aplikasi Face Attendance for Students (FAST)menggunakan teknologi pengenalan wajah berbasis MachineLearning yang terhubung dengan Firebase Realtime Database.FAST melakukan pencatatan kehadiran mahasiswa secaraotomatis dengan memanfaatkan Google ML Kit dan FaceNet,sementara Firebase berfungsi sebagai tempat penyimpanandata utama. Hasil analisis mengindikasikan bahwa sistemmenunjukkan latensi pengenalan wajah antara 36–182 ms(median 162 ms) dan pencatatan presensi antara 2–39 ms(median 4 ms), memastikan respon yang cepat dan efisien.Aplikasi ini juga menunjukkan efisiensi dalam penggunaansumber daya, dengan pemakaian memori hanya 28 MB daritotal 384 MB yang ada. Dengan kinerja tersebut, FAST menjadijawaban inovatif dan efisien untuk presensi perkuliahan. Kata kunci — presensi, pengenalan wajah, Firebase, MachineLearning, efisiensi sistem.
Implementasi Desain UI/UX untuk Meningkatkan Efisiensi Presensi Mahasiswa pada Aplikasi FAST : Face Attendance for Student Akmal , Octa Ryo; Usman , Uke Kurniawan; Putra, Heru Syah
eProceedings of Engineering Vol. 12 No. 3 (2025): Juni 2025
Publisher : eProceedings of Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Aplikasi presensi dengan teknologi facerecognition sedang menjadi tren bagi instansi pendidikan karenaakurasi nya dalam mencatat kehadiran mahasiswa. Denganteknologi ini, proses presensi menjadi lebih terintegrasi danterorganisir sehingga memudahkan dosen untuk memantaukehadiran mahasiswa tanpa cemas akan terjadinya kecuranganatau kesalahan dalam mencatat presensi. Namun, efektivitasaplikasi ini sangat bergantung pada desain antarmuka pengguna(UI) dan pengalaman pengguna (UX) yang baik. Penelitian inibertujuan untuk merancang dan mengimplementasikan desainUI/UX yang interaktif untuk aplikasi presensi mahasiswa denganfokus pada kepuasan pengguna. Penelitian ini menggunakanAndroid Studio sebagai IDE dengan bahasa pemrograman Java.Hasil penelitian membuktikan bahwa desain UI/UX yang efektifdapat meningkatkan kepuasan pengguna terhadap aplikasipresensi. Aplikasi yang dirancang dengan baik memilikiantarmuka yang interaktif, mudah digunakan, dan memberikankepuasan pada pengguna. Kata kunci— desain UI/UX, aplikasi, presensi
Face Recognition Application for Lecture Attendance Using FaceNete Rafieldo, Ricky Marcelino; Usman, Uke Kurniawan; Putra, Heru Syah
Angkasa: Jurnal Ilmiah Bidang Teknologi Vol 17, No 2 (2025)
Publisher : Institut Teknologi Dirgantara Adisutjipto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28989/angkasa.v17i2.3103

Abstract

Student Attendance Systems that still rely on manual or semi-manual methods are often prone to recording errors and misuse, which can disrupt the academic evaluation process. Facial recognition technology can offer a solution by enabling the unique identification of individuals based on facial features and allowing automatic, real-time attendance recording. This study aims to develop a facial recognition attendance system using Google ML Kit and FaceNet in a mobile application. Testing was conducted under various conditions, including different distances, lighting, and the use of accessories, to evaluate the system's reliability in real-world scenarios. The results show 100% accuracy at distances of 50 cm, 100 cm, and 150 cm, although recognition time slowed from 1.328 seconds at 50 cm to 1.963 seconds at 150 cm. Accuracy decreased in low-light conditions, and the simultaneous use of accessories such as hats and glasses reduced accuracy to 78.75%. Additionally, the system exhibited a False Acceptance Rate (FAR) of 10% when tested with faces outside the database. Overall, the developed facial recognition system demonstrates high accuracy under ideal conditions but still requires optimization for varying environmental conditions.
The Linkage of Intergovernmental Transfer and Poverty in Indonesia Putra, Heru Syah
Jurnal Bina Praja Vol 9 No 1 (2017)
Publisher : Research and Development Agency Ministry of Home Affairs

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21787/jbp.09.2017.29-40

Abstract

Decentralization is expected to reduce poverty. Through fiscal decentralization, poverty may be reduced by optimizing intergovernmental grants. However, its effect on poverty is beginning to be questioned after some districts in Indonesia showed slowing performance on poverty reduction despite increasing transfer. Thus, this paper tends to investigate the linkage of intergovernmental transfer (IT) and poverty in Indonesia. By using panel data from 2005 to 2013, the linkage is tested using linear regression model. The result shows that increasing 1% of IT allocation will reduce poverty absolute by 0.12%, or 10% increase of IT will reduce poverty by 1.24%. The intergovernmental transfer also directly affects poverty gap and poverty rate. Increasing 10% of IT will reduce the poverty gap and poverty rate by 9.49% and 31.73%, respectively. Moreover, DAU (unconditional intergovernmental transfer) has a higher effect than DAK (conditional intergovernmental transfer) on poverty eradication. An increase of DAU by 1% will reduce the poverty number by 0.068%, in contrast, DAK only has 0.0418% to reduce poverty. However, as the difference is relatively small, the effectiveness of DAU on poverty is not consistent with the decentralization theory. Unconditional grant must have a significant difference than conditional grant on poverty. It may indicate that the DAU has been spent ineffectively and inefficiently. It may also indicate that it has been spent on not pro-poor policies. Thus, fiscal decentralization in Indonesia needs to be reevaluated in order to support poverty alleviation program.
Determinants of Vote Buying in Local Head Election in Indonesia Putra, Heru Syah
Jurnal Bina Praja Vol 9 No 2 (2017)
Publisher : Research and Development Agency Ministry of Home Affairs

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21787/jbp.09.2017.205-218

Abstract

The local head election in Indonesia suffers from vote buying. However, there is a lack of study compared to vote buying case in Indonesia, especially quantitative study. Therefore, this study aims to fill the gap. The purpose is to estimate the effect of individual and community characteristics on the probability of voter to consider money or gifts in a local head election. This study uses the data from Indonesia Family Life Survey 5 (IFLS5) conducted in 2014/2015 for 29,788 respondents. As the response is a binary data, the Linear Probability Model (LPM) and logit model is utilized. The result shows that both individual and community characteristics affect vote buying in Indonesia. Voters with tertiary education are far less likely to consider money or gift by 29.1% than others. By using logit test, the coefficient is corrected. Voters with a university degree tend to not engage in vote buying by 0.27 times than the others. This study finds other interesting findings that gender matter in vote buying in Indonesia. Female voters tend to consider money or gift more than male by 2.44%. Voters who live in rural areas have a higher probability to consider vote buying by 4.55%. Living in the internet-connected community may reduce the probability of vote buying. The coefficient indicates that those with internet access have less probability to consider money or gift in an election by 1.35%. Living in a community with high social awareness makes voters less vulnerable to vote buying. The coefficient indicates that they have less possibility to consider money by 2.44% than those living in communities with less social awareness. Thus, the strategy to eliminate vote buying should be adjusted to the character of voters in a certain community.
Co-Authors Akmal , Octa Ryo Asahar Johar Deni Yanuar, M. Ikom Edy Saputra funny farady Coastera Mirza Sahputra Muazzinah Nadia Ulfah Nanang Rianto, Nanang Rafieldo, Ricky Marcelino Rizanna Rosemary Rizqi , Mochamad Ilman Yassir Said Fadhil Swandoko, Bagas Tri Syam, Hamdani M Uke Kurniawan Usman Usman , Uke Kurniawan Winny Dian Safitri