Claim Missing Document
Check
Articles

Found 17 Documents
Search

PERANCANGAN SISTEM INFORMASI GEREJA BERBASIS WEBSITE MENGGUNAKAN FRAMEWORK LARAVEL (Studi Kasus: HKBP Sultan Mazmur Pancawati) Annabella Dian Dameria Sinambela; Kamal Prihandani; Chaerur Rozikin
Jurnal Informatika dan Teknik Elektro Terapan Vol 12, No 3 (2024)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v12i3.4840

Abstract

Currently, many churches still use paper or booklets for worship events, which causes paper usage to be very high and inefficient. Based on observations and questionnaires with church members, many feel this method is inefficient as paper is often only used once and then discarded. The church's internal assessment also showed this method resulted in a waste of resources and lack of easy access to information. To address these issues, a dedicated website is needed for HKBP Sultan Psalm Pancawati to deliver information efficiently and effectively. This research designs and develops a web-based church information system using the SDLC method with a prototype approach, involving mutual interaction between developers and users. The steps include needs identification, rapid design, prototype building, system development and testing, and implementation. Testing is done through alpha and beta testing, where alpha testing checks internal smoothness and beta testing uses questionnaires to evaluate external acceptance. Results showed a level of feasibility with a score of 91%, reflecting positive acceptance from users and the effectiveness of the system in meeting the needs of the congregation as well as reducing reliance on paper usage.
Analisis Transaksi Penjualan Pada Recovery.u Computer Menggunakan Algoritma Naive Bayes Almira Dwi Yuliarti; Corrinna Salsabila Amelia; Dewi Ika Sukarno Putri; Chaerur Rozikin
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 3 No. 3 (2023): Desember : Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Pusat Riset dan Inovasi Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v3i3.3144

Abstract

As time passes, the competition in the realm of venture and technologyis quickly increasing, so that business people are competing to expand their business by utilizing existing technology, and also that their business always survives and thrives in the rapid business competition. Sales at Recovery.u Computer are supposed to continue to mount benefit, one of which is by providing products to market demand so that no harm occur. During this time the company often suffers losses because it does not have a system to predict sales. This research has been past perform and attest that the Naïve Bayes Algorithm can be used to predict sales of products and services at Recovery.u Computer. The research data consists of 4 attributes, namely, transaction date, product line, brand, and purchase status obtained from Recovery.u Computer from January 2023 – October 2023. The yield of the estimation that have been it is known that the calculation procces is assisted by WEKA software, by making a possibility table of each variable and an exactness rate of 98,6248% on the test data that has been curried out, and purposeful this can be informed to Recovery.u Computer to do wiser policy in the future.
Pendeteksi Sampah Metal untuk Daur Ulang Menggunakan Metode Convolutional Neural Network Ranti Holiyanti; Sukma Wati; Ikbal Fahmi; Chaerur Rozikin
Jurnal Teknik Informatika dan Sistem Informasi Vol 8 No 1 (2022): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v8i1.4492

Abstract

Waste is part material that has no value within the scope of production. If you no longer need it, metal cans can take about 80 to 200 years to decompose. CNN is part of the supervised learning method that exists in deep learning, where those who have expertise in representing images or images from several categories increase recognition, namely in classifying objects, doing scene recognition, and detecting object detection. In this study, using the CNN method as a development model and applying the ResNet 50 network design, which includes the type Convolutional Neural Network (CNN) that operates by way of working, namely receive an input in the form of an image or images. The input will be carried out by training that is set using the CNN architecture so that later it will produce an output that can recognize objects as expected in knowing the types of cardboard and glass waste. The implementation of this research uses the Python programming language, Anvil, and the TensorFlow and Keras libraries. The system has succeeded in detecting the type of metal waste from general waste and assisting third parties, namely implementing it through the website using Anvil. The input shape for CNN modeling in this study is 512x384 pixels, which has a value of 100 eras, and the data set used contains images of metal waste and general waste found 547 images, resulting in an accuracy of 96%.
Sentiment Analysis Of Indonesia National Team Naturalization Using Bidirectional Encoder Representations From Transformers Diva Ahmad Maulana; Chaerur Rozikin; Aries Suharso
Jurnal Info Sains : Informatika dan Sains Vol. 15 No. 01 (2025): Informatika dan Sains , 2025
Publisher : SEAN Institute

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

Abstract

In this era of rapid development of information technology, the number of internet users is increasing, supported by the popularity of social media as a medium for sharing information and interacting. The X social media platform is one of the media that is often used to convey public opinion. One of the hot issues discussed on X social media is the Indonesian National Team naturalization program. This program has triggered various public responses, both pro and con. This study aims to analyze public sentiment regarding the program using the Bidirectional Encoder Representation from Transformer (BERT) algorithm with the Knowledge Discovery in Database method. Data was collected using scraping techniques on the X social media platform which were then selected and labeled positive, negative, and neutral. Testing the BERT algorithm using the pre-trained indoBERT model was tested by dividing the training and testing data 80:20, and evaluated with a confusion matrix. With a dropout of 0.3, the evaluation results showed the highest accuracy value of 90%, precision 81%, recall 74%, and f1-score 77%. The results of this study are expected to be useful for evaluation materials and to support decision making by related parties.
PENERAPAN PENGENALAN WAJAH MENGGUNAKAN CNN DAN DETEKSI LOKASI HAVERSINE UNTUK PRESENSI SEKOLAH BERBASIS WEB Muhammad Fitra Fajar Rusamsi; Aries Suharso; Chaerur Rozikin
Jurnal Informatika dan Teknik Elektro Terapan Vol. 13 No. 3S1 (2025)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v13i3S1.7485

Abstract

Kehadiran guru merupakan faktor utama dalam mendukung kelancaran proses pembelajaran dan administrasi akademik di sekolah. Namun, sistem presensi manual yang masih digunakan, memiliki berbagai kendala seperti kurangnya transparansi data, tidak efisien, risiko manipulasi data, hingga kesulitan memverifikasi lokasi dan wajah guru secara akurat. Menyikapi tantangan tersebut, dibutuhkan inovasi yang dapat meningkatkan efisiensi dan transparansi data, khususnya dalam hal kehadiran guru. Penelitian ini bertujuan untuk mengembangkan sistem presensi guru berbasis web dengan teknologi pengenalan wajah (face recognition) menggunakan OpenCV dan model CNN pre-trained, serta validasi lokasi berbasis metode Haversine. Integrasi teknologi ini memungkinkan presensi tidak hanya dapat memverifikasi identitas guru, tetapi juga memastikan kehadiran dilakukan di tempat dan waktu yang sesuai. Total citra wajah yang didapatkan kurang lebih 50 guru. Metode yang digunakan dalam proses ini adalah Waterfall. Pada pengembangan sistem ini menggunakan laravel serta python sebagai face recognition yang nantinya dikirim sebagai API lalu diterima oleh Laravel. Proses pengujian dilakukan dengan tiga kondisi untuk masing-masing metode. Pada pengujian pengenalan wajah, dari tiga sampel wajah yang diuji, hanya satu yang tidak berhasil dikenali, yaitu wajah yang tertutup masker. Sementara itu, pada pengujian validasi lokasi, sistem berhasil mendeteksi lokasi guru dengan akurat.
PERANCANGAN DATA PIPELINE UNTUK ANALISIS POLA PERJALANAN DAN PERMINTAAN LAYANAN TRANSJAKARTA Resti Dwi Artika; Nadiyah Nur Rafifah; Putri Ayu Dina; Chaerur Rozikin
Jurnal Informatika dan Teknik Elektro Terapan Vol. 13 No. 3S1 (2025)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v13i3S1.8051

Abstract

Mobilitas penduduk di DKI Jakarta semakin kompleks seiring meningkatnya urbanisasi, menuntut efisiensi sistem transportasi publik seperti Transjakarta. Pemanfaatan big data menjadi solusi strategis untuk memahami pola perjalanan penumpang dan mendukung perencanaan layanan berbasis data. Penelitian ini bertujuan merancang pipeline data Transjakarta end-to-end yang terotomatisasi, scalable, dan siap digunakan untuk analisis spasial-temporal. Metode penelitian yang digunakan adalah pendekatan kuantitatif eksploratif dengan memanfaatkan dua dataset sekunder, yaitu data transaksi penumpang (tap-in/tap-out) dan data koordinat halte, yang diolah menggunakan bahasa pemrograman Python. Pipeline dikembangkan melalui enam tahapan utama: collect, ingest, clean, integrate, analyze, dan visualize. Hasil penelitian menunjukkan bahwa pipeline mampu meningkatkan efisiensi proses ETL, menghasilkan data bersih yang siap analisis, serta memungkinkan visualisasi pola perjalanan dan jam sibuk secara otomatis. Kelebihan sistem terletak pada fleksibilitas dan kemudahan replikasi, sementara keterbatasannya adalah belum mendukung pemrosesan real-time. Secara keseluruhan, penelitian ini berkontribusi terhadap pengembangan sistem pengolahan data transportasi publik berbasis big data yang dapat mendukung pengambilan keputusan operasional secara lebih cerdas dan adaptif.
IMPLEMENTATION OF BANDWIDTH MANAGEMENT USING THE PER CONNECTION QUEUE METHOD (CASE STUDY: SMK TRIKARYA) Wisnu Yogi Pamungkas; Chaerur Rozikin; Arip Solehudin
Jurnal Informatika dan Teknik Elektro Terapan Vol. 14 No. 1 (2026)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v14i1.9025

Abstract

The increasing utilization of internet networks at SMK Trikarya has not been supported by optimal bandwidth management, resulting in unequal bandwidth distribution among users and potentially disrupting teaching and learning activities. This study aims to implement bandwidth management using the Per Connection Queue (PCQ) method and to analyze network performance based on Quality of Service (QoS) parameters before and after the implementation. The research method applied is the Network Development Life Cycle (NDLC), which includes analysis, design, simulation, implementation, monitoring, and management stages. QoS testing was conducted by measuring throughput, delay, jitter, and packet loss using the Wireshark application. The results show that the implementation of the PCQ method on MikroTik devices is able to distribute bandwidth fairly based on the number of active connections. Post-implementation QoS analysis indicates more evenly distributed throughput values, reduced delay and jitter, and stable packet loss at 0%. Therefore, it can be concluded that the PCQ method is effective in improving network performance and internet service quality at SMK Trikarya.