Claim Missing Document
Check
Articles

Computer Vision: Deteksi Masker Wajah Prediksi Usia Jenis Kelamin dengan Teknik Deep Learning Menggunakan Algoritma Convolutional Neural Network (CNN) Sopian, Abu; Setiadi, Dedi; Suryatno, Agung; Agustino, Rano
Jurnal Teknologi Informatika dan Komputer Vol. 10 No. 2 (2024): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v10i2.2395

Abstract

Sejak pandemi COVID-19, penggunaan masker wajah menjadi langkah penting untuk mencegah penyebaran virus, memerlukan sistem otomatis untuk mendeteksi kepatuhan penggunaan masker. Teknologi computer vision muncul sebagai solusi potensial untuk mempermudah deteksi penggunaan masker dalam skala besar. Selain itu, teknologi pengenalan wajah telah berkembang pesat, memungkinkan identifikasi atribut lain seperti jenis kelamin dan usia dari gambar wajah. Penelitian ini mengembangkan model deep learning berbasis Convolutional Neural Network (CNN), khususnya MobileNet, untuk mendeteksi masker wajah dan memprediksi atribut wajah seperti jenis kelamin dan usia, meskipun sebagian wajah tertutupi masker. Model ini bertujuan meningkatkan efisiensi deteksi masker serta memberikan informasi demografis yang berguna dalam berbagai bidang, seperti kesehatan, retail, dan keamanan publik. Penelitian ini menggunakan pendekatan eksperimen dengan dataset gambar wajah yang mencakup individu dengan dan tanpa masker, serta data tambahan untuk prediksi jenis kelamin dan usia. Model dilatih dengan teknik transfer learning, dan dilakukan evaluasi menggunakan metrik precision, recall, F1-score, serta mean absolute error (MAE) untuk prediksi usia. Hasil eksperimen menunjukkan akurasi deteksi masker mencapai 99%, sedangkan prediksi jenis kelamin dan usia memiliki akurasi 98,75%, dengan sensitivity 98,5% dan specificity 99%. Implementasi model dalam aplikasi real-time menggunakan OpenCV dan Tkinter menunjukkan latensi deteksi rendah dan responsivitas yang baik. Penelitian ini memberikan kontribusi signifikan dalam pengembangan sistem otomatis berbasis teknologi computer vision untuk aplikasi praktis di berbagai sektor, sekaligus meningkatkan keselamatan publik melalui deteksi masker yang akurat dan cepat.
Design of Application for Reporting Violence Against Women and Children in RT.001 RW.005 KEL.Dukuh with Waterfall Method Sopian, Abu; Setiadi, Dedi
Jurnal Teknologi Informatika dan Komputer Vol. 11 No. 1 (2025): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v11i1.2562

Abstract

Violence against women and children is a violation of human rights that occurs across various layers of society, with a significant increase in Indonesia. Data shows that the number of cases of violence against women and children in East Jakarta reached 302 cases in the first six months of 2024. RT.001 RW.005 in the Dukuh Kramat Jati area is one of the areas facing this issue. In this context, incidents of violence are often not addressed or reported swiftly, leading to victims not receiving the protection they deserve. This study aims to design the "Report Violence Against Women and Children" application using the waterfall method, which is expected to make it easier for residents to report cases of violence directly to the RT and RW administrators. Through needs analysis and data collection, this application will provide an efficient solution for report administration. The benefits of this study are not limited to theoretical aspects but also practical ones, with the hope of increasing public awareness and accelerating the handling of violence cases. The outcome of this study is expected to be an application documentation that can be published and copyrighted, thus being accessible to the wider public. This research underscores the importance of information technology in addressing critical social issues, such as violence against women and children, and contributes to the development of a more responsive and effective reporting application.
Design of GIS-Based Attendance Application at SMA Santika East Jakarta Saputro, Mohammad Ikhsan; Pertiwi, Santhi; Suryatno, Agung; Setiadi, Dedi; Sopian, Abu; Rifqi, Agven Muharis; Agustino, Rano
Jurnal Teknologi Informatika dan Komputer Vol. 11 No. 1 (2025): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v11i1.2569

Abstract

In the digital era and industry 4.0 like today, human resource management (HR) is important for schools. One important aspect in human resource management (HR) in a school is employee attendance. Currently, for employee attendance at SMA Santika East Jakarta, the fingerprint attendance system is still used, which has shortcomings, such as the possibility of misuse of number codes that can lead to falsification of attendance. This study aims to develop an attendance application based on the Geographic Information System (GIS) at SMA Santika East Jakarta to improve the accuracy and reliability of the employee attendance system. In the context of the digital era and industry 4.0, proper employee attendance management is crucial, especially when employees work outside the office. To overcome this problem, this study designs a GIS-based attendance application that is able to track employee locations in real-time when taking attendance, both in the school environment and outside the school. The research methodology involves observation, interviews, and literature studies to obtain relevant data. The development model used is a prototype, which includes needs analysis, design, code development, testing, and system support. The application is developed using the React Native framework and TypeScript programming language, and is integrated with the Odoo system via REST API. With this application, it is hoped that SMA Santika East Jakarta can reduce the risk of attendance falsification and improve human resource management, as well as increase operational efficiency and accuracy of employee attendance data.
Implementation of Dijkstra's Algorithm for Nearest Location Search on Fire Extinguishing Robot Narji, Mohammad; Setiadi, Dedi
Jurnal Teknologi Informatika dan Komputer Vol. 11 No. 1 (2025): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v11i1.2581

Abstract

Today's technological knowledge has experienced a lot of progress, including in robotic technology. Of course, this field is becoming more interesting to study, seeing its increasingly widespread use in various aspects of human life that are increasingly automated. Real-life automation in machine representation is a value in itself from the implementation of a robot. Along with the development of the era, the world of information technology is currently developing very rapidly. In line with the rapid development of information technology, the need for time efficiency is a very important issue today. One of them is finding the shortest path from the original location to the destination location. In achieving optimal time efficiency, good management is needed by applying directed concepts and increasingly modern and sophisticated technology. Information media is very much needed in a computerized way to make it easier for fire extinguishing robots to find the location of fire points. The use of the Dijkstra Algorithm in the Nearest Route Search Application was chosen to be applied to the fire extinguishing robot application, to solve problems step by step in finding the nearest route. The theory used in this study uses Graph theory, Dijkstra's Algorithm. The purpose of this study is to find out how fire extinguishing robots find the shortest route and how the Dijkstra algorithm method can be used to find the location of the fire source with the shortest route.
Designing an Overtime Request Information System Using the SDLC Method at PT. Laju Omega Digital Setiadi, Dedi; Sopian, Abu; Mubarok, Royhan Ibnu; Widyahastuti, Febrianti
Jurnal Teknologi Informatika dan Komputer Vol. 11 No. 2 (2025): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v11i2.2922

Abstract

The development of information technology has had a significant impact on human resource management, including the process of submitting overtime requests to employees. This process is crucial to ensure optimal productivity, especially in companies with many divisions and employees. PT. Laju Omega Digital still uses manual methods for recording overtime, which causes delays in the process, difficulties in tracking data, and a lack of transparency in overtime approvals. Therefore, a web-based system is needed that can automate and improve the efficiency of managing overtime requests. This study aims to design and develop a web-based information system that allows employees to submit overtime digitally, as well as facilitates admins in managing overtime request data. This system is built using the Laravel framework with a Bootstrap-based design to be more responsive and easy to use. The main features developed include a login system, an overtime request form, overtime verification and approval, and data recapitulation for further analysis. The research methods used include observation, interviews, and literature studies. System development is carried out using the System Development Life Cycle (SDLC) model, including needs analysis, system design, implementation, testing, and evaluation. The research results show that the developed system can improve the efficiency of overtime requests, reduce recording errors, and provide greater transparency in the approval process. With this system's implementation, PT. Laju Omega Digital can improve productivity and the quality of human resource management.
Genetic Improvement of Araucaria cunninghamii for Enhanced Industrial Pulp Production Pamungkas, Bayu; Setiadi, Dedi; Baskorowati, Liliana; Mashudi; Pudjiono, Sugeng; Nurtjahjaningsih, Ida Luh Gede; Susanto, Mudji; Hendrati, Rina Laksmi; Sumardi; Fauzan, Yusuf Sigit Ahmad; Wirabuana, Pandu Yudha Adi Putera
Jurnal Sylva Lestari Vol. 13 No. 3 (2025): September
Publisher : Department of Forestry, Faculty of Agriculture, University of Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jsl.v13i3.1163

Abstract

Araucaria cunninghamii has significant potential as a long-fiber pulpwood source in Indonesia; however, its utilization remains limited due to its dependence on imported raw materials. This study presents the results of a first-generation progeny trial designed to evaluate genetic variation and identify superior genotypes for future breeding programs. This study was conducted in Bondowoso, East Java; the experimental was included 80 families from six provenances (Fakfak, Jayapura, Serui, Wamena, Manokwari, and Queensland) and designed by a Randomized Complete Block Design (RCBD); comprised of 6 provenances, 80 families, 4 blocks, 4 trees per plot with a spacing of 4 m ´ 2 m. After six years, the survival rates ranged from 98.30% to 99.61%, indicating a strong potential for adaptability. Significant differences were observed among families for height, diameter, and volume growth traits. Heritability estimates for height, diameter, and volume at the individual level were 0.30, 0.25, and 0.27, respectively, and 0.48, 0.45, and 0.47 at the family level. Strong genetic correlations were found between height and diameter (r = 0.99), suggesting the potential for indirect selection through breeding. These findings highlight the genetic potential of A. cunninghamii for sustainable pulp production and inform future breeding strategies that focus on growth, adaptability, and wood quality. Keywords: Araucaria cunninghamii, genetic variation, progeny test, pulpwood, heritability, provenance trial
PEMESANAN PRODUK SOUVENIR BERBASIS WEB Gusmaliza, Debi; Sasmita, Sasmita; Setiadi, Dedi
(JITEK)Jurnal Ilmiah Teknosains Vol 9, No 2/Nov (2023): JiTek
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/jitek.v9i2/Nov.17303

Abstract

Pagar Alam City is known as a tourist city. Apart from being rich in ancient relics in the form of megalith stones, Pagar Alam is also famous for its natural beauty. This city makes agricultural tourism a direction for developing the people's economy, one of which is a business that sells souvenirs, where tourists from inside and outside always buy souvenirs as souvenirs for relatives and friends. The problem with ordering at this shop is that it still uses a manual system so the data entered is not computerized. In this research, a web-based souvenir product ordering application will be created. The programming languages used to create this program are Php and MySQL with the help of Visual Studio Code, Adobe Photoshop and Xampp tools. The research method used is the waterfall method which has stages such as the user requirements analysis stage, system design stage, implementation stage, verification stage, and finally the maintenance stage. The final result of this research is the creation of an application that can solve data processing problems quickly, precisely and accurately which is connected to a database, making it easier to create orders and recapitulate monthly order reports quickly and at any time if needed.
Sistem Informasi Keuangan Investasi Reksadana Berbasis Aplikasi Web Setiadi, Dedi; Nabilah, Lily
Ilmu Ekonomi Manajemen dan Akuntansi Vol. 2 No. 2 (2021): Jurnal Ilmu Ekonomi Manajemen dan Akuntansi
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/ileka.v2i2.557

Abstract

Sistem investasi dan literasi keuangan dalam hal pasar modal di Indonesia masih rendah. Hal ini dikarenakan masyarakat Indonesia belum begitu mengenal industri investasi, baik pasar modal dan lainnya dengan baik. Kecenderungan bahwa investasi harus mengeluarkan nominal yang besar berakibat pada terhambatnya literasi keuangan untuk investasi tersebut. Dengan Perkembangan teknologi informasi yang semakin meningkat secara exponensial di era revolusi industri 4.0, maka dibutuhkan sebuah layanan yang mencakup kemudahan akses, bersifat inklusi, dan otomatisasi untuk menjawab permasalahan tersebut. Atas dasar hal tersebut, saya memutuskan untuk melakukan penelitian yang dapat membantu melakukan literasi keuangan kepada masyarakat dengan cara merancang aplikasi perencanaan keuangan dengan instrumen investasi reksadana berbasis progressive web apps menggunakan metode exponential moving average sebagai cara untuk mendapatkan rekomendasi produk reksadana pada saat melakukan transaksi. Aplikasi yang telah dirancang mampu tampil sebagai aplikasi yang user friendly serta dapat memberikan informasi dan pemahaman yang baik tentang industri investasi, sejalan dengan tujuan awal yaitu membantu melakukan literasi keuangan kepada masyarakat.Kata Kunci: PWA, ASP, Scrum Modul, Exponential Moving Average
Optimization Of Agricultural Production In South Sumatera Using Multiple Linear Regression Algorithm Setiadi, Dedi; Sasmita, Sasmita; Mukti, Yogi Isro
Knowbase : International Journal of Knowledge in Database Vol. 4 No. 2 (2024): December 2024
Publisher : Universitas Islam Negeri Sjech M. Djamil Djambek Bukittinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30983/knowbase.v4i2.8754

Abstract

Rice is one of the agricultural commodities in South Sumatra whose productivity level still fluctuates. In 2000, rice production reached 1,863,643.00 kg, then increased to 3,272,451.00 kg, in 2010, but decreased again in 2020 to 2,696,877.46 kg. This instability is influenced by various factors such as land area, rainfall, pest attacks, and fertilizer use. This study aims to optimize rice production by applying machine learning using multiple linear regression algorithms, and the CRISP-DM method, with the stages being business understanding, data understanding, data preparation, modeling, evaluation, and implementation. Data of 1,000 records obtained from farmers were analyzed using Google Collaboratory, resulting in an intercept of -3836,2639, and coefficients for land area of 5,7336, rainfall of 1,2710, pests of 6,1153, urea of 1,6226, and phonska of 1,2581. To evaluate the accuracy of rice production predictions based on these independent variables, calculations were made on the RMSE value and analysis of the coefficient of determination. The results were that the RMSE value was recorded at 17065084,9641, and the coefficient of determination (R²) was 0,6487, indicating that around 64,87 % of the variability in rice production can be explained by independent variables such as land area, rainfall, pest attacks, use of urea fertilizer, and phonska, while the remaining 35,13 % was influenced by other factors.
Viabilitas Biji Sengon Penyimpanan 6 Bulan dan 23 Tahun Baskorowati, Liliana; Setiadi, Dedi; Fauzi, Mohammad Anis
Prosiding SNPBS (Seminar Nasional Pendidikan Biologi dan Saintek) 2017: Prosiding SNPBS (Seminar Nasional Pendidikan Biologi dan Saintek)
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (229.659 KB)

Abstract

Sengon yang banyak dikembangkan oleh masyarakat di Jawa karena cepat tumbuh dan mempunyai pangsapasar kayu yang bagus. Hal tersebut menyebabkan permintaan akan bibit sengon di masyarakat sangat tinggi.Pembibitan sengon selama ini dilakukan melalui penyemaian biji yang didapat dari tanaman-tamanan sengondisekitarnya. Untuk menunjang penyediaan bibit, maka penelitian ini dilakukan dengan tujuan untukmengetahui viabilitas biji sengon setelah penyimpanan yang lama (23 tahun) dan penyimpanan selama 6bulan. Penelitian dilakukan di Balai Besar Penelitian dan Pengembangan Bioteknologi dan PemuliaanTanaman Hutan pada bulan Januari sampai Maret 2017. Benih sengon yang digunakan adalah benih sengonyang dieksplorasi dari 5 provenan (daerah asal) di Wamena dan Jawa untuk uji umur 6 bulan; serta 5provenan dari Wamena untuk uji umur 23 tahun oleh tim peneliti sengon B2P2PBPTH. Benih sengontersebut disimpan di dalam plastik tertutup yang dimasukkan ke dalam botol plastik dan disimpan dalamDCS (Dry Cold Storage) dengan suhu -5oC. Pengujian viabilitas benih dilakukan dengan menabur benihmasing masing 25 biji menggunakan petridish, dan jumlah benih yang berekecambah diamati pada hari ke 2.5 dan 7. Pertumbuhan tinggi semai umur 1 bulan dicatat, untuk mengetahui laju pertumbuhannya. Hasilpenelitian memperlihatkan bahwa perkecambahan maksimal terjadi pada hari ke 7 dan tidak terjadipenambahan kecambah pada hari ke 9. Kemampuan kecambah sengon dengan lama simpan 6 bulanmenunjukkan perbedaan yang nyata antar provenan dengan nilai F hitung = 3.391 dan P (sig) = 0.000;sedangkan yang dengan lama simpan 23 tahun tidak berbeda secara nyata antar provenan. Rerata persenkecambah untuk benih dengan penyimpanan 6 bulan : 81,99% sedangkan dengan penyimpanan 23 tahun :60,31%. Analisis data pengukuran tinggi semai sengon umur 1 bulan dari benih yang disimpan selama 6bulan menunjukan perbedaan yang sangat nyata antar provenan; semai sengon dari Elagiama mencapai reratatinggi 8.67 cm; pertumbuhan tinggi terendah adalah semai yang berasal dari Wonosobo (5.98 cm). Variasipertumbuhan semai sengon umur 1 bulan antar provenan Wamena juga ditunjukkan dari benih sengon yangsudah disimpan selama 23 tahun. Secara umum benih yang masih baru (disimpan 6 bulan) mempunyaikemampuan tumbuh yang lebih baik dibandingkan dengan benih yang sudah lama tersimpan (23 tahun). Daripenelitian ini dapat disimpulkan bahwa biji sengon dapat disimpan di DCS dalam waktu yang lama,meskipun terjadi penurunan viabilitas.
Co-Authors Akbar, Prima Soultoni Amany, Fadhila Azhar Amin Sakaria, Muhammad Annisa, Nabila Nur Arief, Riskal Arif, Alfis Asri Insiana Putri bayu pamungkas Budi Leksono Edowinsyah, Edowinsyah Effendi, Muhammad Ridwan Eko Pujiono Eliza Eliza Esmeralda, Gracia Nadya Fadillah, Agung Fadly, Fery Fauzan, Yusuf Sigit Ahmad Fauzi, Mohamad Anis Fauzi, Mohammad Anis Febrianto Febrianto, Febrianto Fitriani, Novita Fitriansyah, Ahmad Gusmaliza, Debi Hamdan Adma Adinugraha Hapzi Ali Harahap, Irma Suryani Haryono, Yudhie Hasna, Tri Maria Ida Sugiarti Ida Wahyuni ILG Nurtjahjaningsih, ILG Imas Masturoh Iskandar, Riadho Julfia, Fenty Tristanti Junaedi, Fadil Ahmad Liliana Baskorowati Masdalipa, Risnaini masda Mashudi Mashudi Mashudi Mohammad Ikhsan Saputro, Mohammad Ikhsan Mubarok, Royhan Ibnu Muchtar, Asyari Mudji Susanto Mursid, Asep Nabilah, Lily Narji, Mohammad Nasrullah, Abdi Nurtjahjaningsih, Ida Luh Gede Oktaria, Anik Paryanti, Atik Budi Pertiwi, Santhi Puspita, Desi Radiati, Ani Rano Agustino Rifqi, Agven Muharis Rina Laksmi Hedrati Rina Laksmi Hendrati Rizal, Agus Rosmawati, Henni Rossa, Mohamad Adila S. Sugiharto Sari, Fajar Yunita Sasmita Sasmita Satryawati, Eka Sinaga, Fius Bryan Nigel M. Sondang Sibuea Sopian, Abu Sugeng Pudjiono, Sugeng Suhenda, Andi Sukawan, Ari Sumardi Sumardi . Sunaryo, Yaya Suryani Kurniasih, Dewi Lena Suryani Suryatno, Agung Sutrisno, Sutrisno Syahri, Riduan Tata Sutabri Tri Rini Nuringtyas Ulfah Fauziah Umam, Ahmad Chatibul Untoro, Ari Bayu Wahyuni, Tariska Desri Wibisono, Mochamat Gunawan Widyahastuti, Febrianti Wirabuana, Pandu Yudha Adi Putera Wulandari, Robeca Yogi Isro Mukti, Yogi Isro Yohanes Bowo Widodo Zulkarnain, Muhammad Haris