Claim Missing Document
Check
Articles

Found 10 Documents
Search

Membangun Konsep Teknis Aplikasi dan Pemanfaatan Metode dalam Penulisan Tugas Akhir Fakultas Ilmu Komputer Sawali Wahyu; Jefry Sunupurwa Asri; Silvia Ratna Juwita; Adi Widiantono; Iksan Ramadhan
COMSERVA : Jurnal Penelitian dan Pengabdian Masyarakat Vol. 2 No. 10 (2023): COMSERVA : Jurnal Penelitian dan Pengabdian Masyarakat
Publisher : Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59141/comserva.v2i10.628

Abstract

Community service activities organized by LPPM Esa Unggul University are carried out using webinars. This activity is a means of sharing knowledge for students of the Faculty of Computer Science regarding final assignments. The Final Assignment is a routine activity at the end of the semester carried out by students and their supervisors at the beginning of the preparation stage. Support for the final project concept can provide opportunities for students with their supervisors to hold discussions to find solutions to the problems of the research topics to be taken. In this abdimas scientific forum webinar, it was held to build concepts and technical applications in writing the final project for students of the Faculty of Computer Science. The result of this community service is to provide an overview of computer science faculty students in building concepts both in terms of application, methodology and writing procedures that are useful for preparing the final project. The Webinar presented several techniques and practices in making applications including: Introduction to Mobile Application Concepts and Methods, Data Management with Machine Learning, Compilation of Engineering Requirements and Creating Websites using the Code Igniter (CI) Framework. From the webinar material, it can help students explore topics and final project research concepts that will be carried out by students during the preparation of the Final Project.
Optimisasi Virtual Geometry Group Untuk Klasifikasi Citra Digital Pada Kanker Serviks Jefry Sunupurwa Asri
Syntax Literate Jurnal Ilmiah Indonesia
Publisher : Syntax Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (304.224 KB) | DOI: 10.36418/syntax-literate.v7i8.9119

Abstract

Optimisasi Jaringan Virtual Geometry Group untuk Klasifikasi Kanker Serviks ini membahas tentang pengembangan jaringan VGG terhadap pengklasifikasian histogram kanker serviks. Penelitian ini bertujuan untuk membuat arsitektur jaringan VGG terhadap pengklasifikasian kanker serviks sebagai alat bantu bagi para peneliti citra gambar untuk mendapatkan arsitektur yang optimal dalam mengenali multi kelas berbagai objek citra digital. Citra gambar yang dijadikan objek penelitian adalah histogram kanker serviks. Penelitian ini dimulai dengan melakukan 3 percobaan untuk menentukan detail parameter yang digunakan. Sebagai landasan yaitu convolutional layer dengan parameter Epoch, dropout, jumlah FC untuk mendapatkan hasil berupa data akurasi, presisi, recall dan CPU Time. Digunakan 3 model percobaan yaitu model 1 modified VGG, model 2 yaitu kombinasi modified VGG dengan V3 inception, dan model 3 yaitu VGG 16 Original. Percobaan terbaik didapatkan dari Epoch 30, dropout 0.2 dan FC 2 layer.
Perbandingan Algoritma Regresi Linear Sederhana dan Regresi Polinomial Dalam Prediksi Jumlah Penumpang Kereta Api Di Wilayah Jabodetabek Rohman, Ubaedillah; Sunupurwa Asri, Jefry; Ariessanti, Hani Dewi; Wahyu, Sawali
Pengembangan Riset dan Observasi Teknik Informatika Vol 12 No 1 (2025)
Publisher : Universitas Serang Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30656/protekinfo.v12i1.9842

Abstract

Intisari— Di era digital saat ini pertumbuhan data semakin mengalami peningkatan yang signifikan sehingga memerlukan solusi untuk analisis data yang efisien dan efektif. Machine learning menjadi solusi dikarenakan teknologi ini banyak digunakan di berbagai sektor. Diantara teknik machine learning algoritma regresi linear sederhana dan regresi polinomial berperan dalam melakukan analisis prediksi. Tujuan dari penelitian ini adalah membandingkan kinerja algoritma regresi linear sederhana dan regresi polinomial dalam prediksi jumlah penumpang kereta api di wilayah jabodetabek. Hasil penelitian akan menentukan manakah algoritma yang lebih akurat dalam memprediksi. Dari hasil penelitian regresi polinomial order 3 mendapatkan hasil akurasi tertinggi dengan R-Square 0.8983, MAPE 0.0704, dan RMSE 1446.6222 dibandingkan dengan regresi linear sederhana dengan R-Square 0.7943, MAPE 0.1013, dan RMSE 1713.8127. Kata kunci— Perbandingan, Regresi linear sederhana, Regresi polinomial, Prediksi, Jumlah penumpang kereta   Abstract— In today's digital era, data growth is increasing significantly, requiring solutions for efficient and effective data analysis. Machine learning is the solution because this technology is widely used in various sectors. Among the machine learning techniques, simple linear regression algorithms and polynomial regression play a role in conducting predictive analysis. The purpose of this study is to compare the performance of simple linear regression algorithms and polynomial regression in predicting the number of train passengers in the Jabodetabek area. The results of the study will determine which algorithm is more accurate in predicting. From the results of the study, polynomial regression order 3 obtained the highest accuracy results with R-Square 0.8983, MAPE 0.0704, and RMSE 1446.6222 compared to simple linear regression with R-Square 0.7943, MAPE 0.1013, and RMSE 1713.8127. Keywords— Comparison, Simple linear regression, Polynomial regression, Prediction, Number of train passengers.    
IMPLEMENTASI PERBANDINGAN YOLO V8 DAN YOLO V11 DALAM PENERAPAN TATA TERTIB BERPAKAIAN DI LINGKUNGAN KAMPUS STUDI KASUS UNIVERSITAS ESA UNGGUL KAMPUS BEKASI Yudhi, Muhammad Febri; Erzed, Nixon; Yulhendri, Yulhendri; Asri, Jefry Sunupurwa
Kohesi: Jurnal Sains dan Teknologi Vol. 7 No. 3 (2025): Kohesi: Jurnal Sains dan Teknologi
Publisher : CV SWA Anugerah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.3785/kohesi.v7i3.11680

Abstract

The consistent enforcement of dress code regulations is an important approach to creating an ethical campus environment. This study aims to develop an automated dress code violation detection system utilizing artificial intelligence technology with the the YOLOv8 and YOLOv11 algorithm algorithm. The system is designed to detect categories of compliant and non-compliant clothing in real-time through cameras and provide automatic notifications when violations are detected. The model, trained with a dataset of clothing images, is evaluated using metrics such as precision, recall, and mean Average Precision (mAP). Training results show that the model achieves high accuracy in detecting dress code violations, supporting the goal of enhancing monitoring efficiency and reducing the violation rate. At Esa Unggul University, Bekasi Campus, this system also contributes to modernizing campus management through technology, fostering the creation of a disciplined academic environment aligned with the values of educational institutions.
Penerapan Algoritma BM25 dalam Pencarian Lowongan Pekerjaan pada Website Job Portal Kheng, Tek; Asri, Jefry Sunupurwa; Wahyu, Sawali; Yulhendri, Yulhendri
Bulletin of Computer Science Research Vol. 5 No. 5 (2025): August 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i5.760

Abstract

The development of the digital era has grown rapidly all the time which has significantly changed the job search process for job applicants, making Online Job Portals one of the main places in human resource recruitment activities, however, the effectiveness of Job Portals Job search still has fundamental weaknesses such as the job search technology used still uses simple string matching which can cause less relevant search results and reduce the quality of user experience in applying for jobs. This study was conducted to improve the quality of job vacancy search results on Job Portal A Career by applying the Okapi BM25 algorithm. This research method uses a Rapid Application Development (RAD) development approach, such as designing a client server architecture with Next.js as the frontend, ASP.NET Core as the backend and PostgreSQL as the main database. The BM25 algorithm is integrated directly into the database using the VectorChord BM25 extension to calculate the search relevance score with the user inputted query. In testing with the query “accelist the quality support career IT need”, the system displays 800 of 1,011 documents (79.13%) with a non-zero relevance score. Furthermore, evaluation through User Acceptance Testing (UAT) showed a user satisfaction rate of 91.2%, confirming that BM25 is capable of displaying the most relevant results at the top of the rankings and supporting the effectiveness of the search system. The results of this study can be concluded that the BM25 algorithm is a more effective and efficient search solution with high scalability potential for application to other web-based job search systems.
RANCANG BANGUN SISTEM ABSENSI BERBASIS MOBILE DENGAN MEMANFAATKAN PENGENALAN WAJAH (STUDI KASUS : PT. GINSA INTI PRATAMA) Sitanggang, Josua Pangihutan; Sunupurwa Asri, Jefry; Hermansyah, Hermansyah; Sutanto, Imam
Jurnal Sistem Informasi, Teknik Informatika dan Teknologi Pendidikan Vol. 5 No. 1 (2025): Jurnal Sistem Informasi, Teknik Informatika dan Teknologi Pendidikan
Publisher : Utiliti Project Solution

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

Abstract

Sistem absensi berbasis sidik jari yang digunakan di PT. Ginsa Inti Pratama masih sering menimbulkan kendala, misalnya sulit terbaca ketika jari karyawan kotor atau terluka, pencatatan waktu yang kurang akurat sehingga memerlukan koreksi manual, serta keterbatasan dalam mendukung karyawan yang bekerja di luar kantor. Melihat permasalahan tersebut, penelitian ini berfokus pada perancangan dan pembangunan sistem absensi berbasis mobile dengan memanfaatkan teknologi pengenalan wajah dan validasi lokasi menggunakan Global Positioning System (GPS). Metode pengembangan yang dipilih adalah Prototyping, dimulai dari komunikasi awal dengan pengguna, perancangan, pembangunan, pengujian, hingga evaluasi melalui umpan balik. Sistem dibangun menggunakan Flutter untuk aplikasi mobile, Flask sebagai backend dengan dukungan Multi-task Cascaded Convolutional Networks (MTCNN) dan FaceNet untuk deteksi serta verifikasi wajah, serta Firebase untuk autentikasi dan penyimpanan data. Validasi lokasi diterapkan dengan menghitung jarak pengguna terhadap lokasi kantor menggunakan rumus Haversine. Hasil pengujian menunjukkan sistem berjalan sesuai harapan dan mendapatkan tanggapan positif dari pengguna, terutama dalam hal kemudahan penggunaan dan peningkatan efisiensi kerja. Dengan demikian, sistem ini dapat menjadi alternatif modern yang lebih fleksibel dan efektif dibandingkan absensi berbasis sidik jari
Pelatihan Pengenalan Search Dan Collecting Metadata Ter-Indeks Dimensions AI Sinkronisasi Dengan Mendeley Setiawan, Iwan; Martaseli, Evi; Anwar, Nizirwan; Asri, Jefry Sunupurwa; Ramadhan, Iksan; Herwanto, Agus; Arfian, M. Hadi; Novita, Diana; Widyawan, Tri Ismardiko
Journal Of Human And Education (JAHE) Vol. 4 No. 1 (2024): Journal Of Human And Education (JAHE)
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jh.v4i1.648

Abstract

Mendeley perangkat aplikasi reference manager (desktop/web) yang dapat mengintegrasikan pada platform academic social network untuk berkolaborasi pengutipan judul publikasi untuk menghasilkan suatu artikel dan ter-indeks. Aplikasi ini sangat memudahkan pengguna dalam mengelola sejumlah judul artikel dan memudahkan peneliti dalam men-sitasi sehingga tersusun dalam daftar pustaka, dengan style tertentu yang disesuaikan dari pihak penerbit (Harvard, APA 6th, IEEE, Vancouver dan sejenisnya). Pengabdian mempunyai tujuan dan manfaat bagi peserta penelusuran dan penyusunan daftar Pustaka suatu karya ilmiah (nasional/internasional). Metode yang digunakan pelatihan ini dengan (1) ceramah daring; (2) penyajian tutorial bagaimana mengoperasikan reference manager mendeley (online/offline) dengan baik dan benar serta sesuai dengan kaidah penulisan. Dikarenakan pada Mendeley versi desktop (gratis) batas penyimpanan hanya memori sebesar 2 GB, bisa dalam format pdf/ris/bib dapat diupload secara manual maupun otomatis. Dan dalam pelatihan ini akan memamparkan bagaimana cara mengintegrasikan Mendeley dengan Dimension AI, pengguna dapat menelusuri nama penulis, nama jurnal/konferensi, ISSN, ISBN, DOI, penerbit dan tanggal terbit artikel tersebut. Dari hasil pelatihan pasca pemamparan materi dan diskusi serta pendampingan para peserta (mahasiswa dan dosen) memperoleh kemudahan dalam mengoperasikan Mendeley dan Dimensions AI, mengutip referensi (ris/bib) dengan mudah sekali, akurasi, sederhana, effisien dan effektif dengan hasil akhir tersusun daftar pustaka (MyLibrary).
Pengujian Keamanan Website dengan Metode Penetration Testing (Studi Kasus: Universitas Esa Unggul) Septian, Ferby; Arfian, Muhamad Hadi; Asri, Jefry Sunupurwa; Tjahjono, Budi
Innovative: Journal Of Social Science Research Vol. 4 No. 5 (2024): Innovative: Journal Of Social Science Research
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/innovative.v4i5.15197

Abstract

Perkembangan era digital di Indonesia telah membawa manfaat dan transformasi positif, namun juga menimbulkan tantangan keamanan terkait risiko peretasan dan kebocoran data. Keamanan website menjadi sebuah komponen penting yang tidak bisa dianggap remeh, sehingga website perpustakaan Universitas Esa Unggul memerlukan perlindungan maksimal terhadap ancaman keamanan yang terus berkembang. Penelitian ini bertujuan untuk mengidentifikasi dan mengatasi risiko keamanan melalui pengujian keamanan pada website perpustakaan Universitas Esa Unggul menggunakan metode penetration testing dengan pendekatan black-box, serta memanfaatkan OWASP Top 10 2021 sebagai acuan informasi kerentanan. Pengujian keamanan website berhasil dilakukan melalui beberapa tahapan penetration testing, yaitu reconnaissance, scanning, vulnerability assessment, exploitation, dan reporting. Hasil penelitian ini menunjukkan bahwa website perpustakaan Universitas Esa Unggul memiliki kerentanan yang tercantum dalam OWASP Top 10 2021, dengan 2 jenis kerentanan berisiko tinggi yaitu broken access control dan security misconfiguration, serta 1 kerentanan berisiko rendah yaitu cryptographic failures. Berdasarkan hasil temuan tersebut, rekomendasi perbaikan yang dapat diberikan adalah dengan melakukan konfigurasi ulang terhadap akses kontrol untuk mencegah akses yang tidak sah, menambahkan secure flag pada cookie guna memperkuat enkripsi, serta menerapkan security header untuk mencegah berbagai serangan cyber. Penelitian ini diharapkan dapat meningkatkan keamanan website perpustakaan Universitas Esa Unggul, serta dapat menjadi referensi dalam melakukan pengujian kemanan.
MENGANALISIS PENDEKATAN SELF HEALING PADA SISTEM BERBASIS SOA DAN MICROSERVICE (PAYMENT SERVICE) Farhan, Muhammad; Sobri, Mukhamad Asep; Alindya, Yashinta; Rismayanti, Irna; Ardiansyah, Najib; Maulana, Fandi Fajar; Asri, Jefry Sunupurwa
Innovative: Journal Of Social Science Research Vol. 5 No. 4 (2025): Innovative: Journal Of Social Science Research
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/innovative.v5i4.20850

Abstract

The rapid development of information technology has driven the adoption of distributed system architectures such as Service-Oriented Architecture (SOA) and Microservices, especially in the domain of digital payment services. While both approaches offer high flexibility and scalability, they also present significant challenges related to system complexity and service failure risks. This study aims to analyze the implementation of self-healing system concepts in addressing these challenges. A qualitative descriptive method is employed through literature reviews, technical documentation analysis, and industry case studies. The results reveal that implementing self-healing systems using techniques such as real-time monitoring, circuit breakers, health checks, and auto-recovery significantly enhances the reliability and availability of SOA and microservices-based payment systems. Self-healing mechanisms contribute to reducing system downtime, improving resilience, and maintaining service stability in the face of disruptions or traffic spikes.
Penerapan Clean Arsitektur Menggunakan Mobile Platform Berbasis Flutter Untuk Aplikasi Layanan Kapal Putri, Amanda; Asri, Jefry Sunupurwa; Anwar, Nizirwan; Widiantono, Adi
IKRA-ITH Informatika : Jurnal Komputer dan Informatika Vol. 9 No. 1 (2025): IKRAITH-INFORMATIKA Vol 9 No 1 Maret 2025
Publisher : Fakultas Teknik Universitas Persada Indonesia YAI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37817/ikraith-informatika.v9i1.4380

Abstract

Indonesia's mobile technology adoption rate of 77.02% provides a great opportunity forcompanies to improve their services through mobile platforms. PT ABC, a ship service providerfor various needs, currently only uses web-based applications and needs a mobile-based shipservice application to increase efficiency and flexibility. This research aims to implement CleanArchitecture on a Flutter-based mobile platform to improve the structure and facilitate codemaintenance in ship service applications. The research method used is the prototyping method,with stages including Communication, Quick Plan, Modelling Quick Design, Prototype Formationand Deployment Delivery & Feedback. This approach enables faster application development,earlier identification of potential changes, and reduced risk of failure or mismatch with user needs.The results showed that the application of Clean Architecture in mobile-based ship service applications was successfully implemented so that it provided ease of maintenance. Blackboxtesting with 10 test cases ensures that the application functions as expected and is ready to be usedby PT ABC. User Acceptance Testing also shows that this application meets the needs of users andincreases the company's responsiveness to market changes, the test results reached 86.83%. Withthe division of business logic into usecases folders, the overall efficiency of development, flexibilityof change, and ease of maintenance of the system is increased. In conclusion, Clean Architectureproved to be the right solution to optimise PT ABC's business operations, facilitate applicationmaintenance and testing, and improve code understanding and readability for developers