Claim Missing Document
Check
Articles

Found 5 Documents
Search
Journal : SAINTEK

Aplikasi Sistem Pendukung Keputusan Pemilihan Karyawan Terbaik Berbasis Website Menggunakan Metode SAW Pada PT. Lion Super Indo Andri Firmansyah; Muhammad Dicky Chandra
Prosiding Sains dan Teknologi Vol. 3 No. 1 (2024): Seminar Nasional Sains dan Teknologi (SAINTEK) ke 3 - Januari 2024
Publisher : DPPM Universitas Pelita Bangsa

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

Abstract

Employee performance quality is a key factor in a company’s progress, making objective and accurate evaluation essential in selecting the best employee. At PT. Lion Superindo Marketing Division, the selection process for the best employee is still conducted manually using Microsoft Excel, which may lead to inaccuracies in decision-making. This study aims to develop a web-based decision support system using the Simple Additive Weighting (SAW) method to improve efficiency and accuracy in performance evaluation. The system was developed using PHP, JavaScript, and Bootstrap, with MySQL as the database. The implementation results show that the SAW method accelerates the calculation process and produces more objective decisions. Based on the calculation results, alternative A9, Adam Alfian, obtained the highest preference value of 0.97 and was selected as the best employee. The developed system effectively supports more efficient and accurate decision-making.
Pengembangan Aplikasi Pengadaan Barang Pada Koperasi Karyawan Dan Warga Al-Muslim Berbasis Web Dengan Metode SDLC Andri Firmansyah; Tri Wahyuni
Prosiding Sains dan Teknologi Vol. 3 No. 1 (2024): Seminar Nasional Sains dan Teknologi (SAINTEK) ke 3 - Januari 2024
Publisher : DPPM Universitas Pelita Bangsa

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

Abstract

The growth of information technology for entrepreneurs in Indonesia is very rapid, especially in the city of Bekasi. Al-Muslim Employees and Citizens Cooperative is one of the businesses engaged in cooperative sales of fulfillment needs within the Al-Muslim Foundation which has a large inventory of goods and needs better management. In carrying out its business processes, the Al-Muslim Employees and Citizens Cooperative has several problems including data processing is still manual by using records only so that it is vulnerable to lost or damaged data. Another problem is human error or people who process data from the process of recording incoming goods data, recording outgoing goods data, recording stock data. The method used in this research is Software Development Life Cycle (SDLC), this method describes the overall software development process to produce quality software and meet the expectations of system users. The result of this research is to build a procurement system to make it easier to control the amount of inventory of each item appropriately and can speed up the production of information on ordering goods so that there is no delay in ordering goods.
Penerapan QR Code Menggunakan Webcam Pada Sistem Absensi Guru Honorer Dengan Metode Rapid Application Development (RAD) di SDN Karang Asih 06 Andri Firmansyah; Sovia Yunanda
Prosiding Sains dan Teknologi Vol. 3 No. 1 (2024): Seminar Nasional Sains dan Teknologi (SAINTEK) ke 3 - Januari 2024
Publisher : DPPM Universitas Pelita Bangsa

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

Abstract

Attendance is a very important process, one of which is in the world of education, of course not only for students, teachers are also required to carry out the attendance process in order to determine the quality of their work as teachers at school. The Attendance System for Honorary Teachers is still very simple at SDN Karang Asih 06. Where the system still uses paper containing signatures. of course this system is still very manual for an educational institution because of the lack of discipline so that there are often obstacles such as data recapitulation, or can be misused by irresponsible parties. System research uses the Rapid Application Development (RAD) method which has 3 main stages, namely: (1) Requirment Planning, (2) Design Process (Design Workshop), (3) Implementation. And the choice of a desktop-based attendance system using this QR Code is because it is more efficient and practical in inputting attendance and conveying information from the results of attendance data. Of course, this system is a new standard in the school environment of SDN Karang Asih 06, which previously took attendance manually using paper. In the early stages of system implementation, users must input their attendance using the C# programming language (Sharp), and the system stores attendance data in the MySQL database which can be used as attendance information. And it is hoped that this attendance system can be better and can improve the shortcomings in the attendance system that has been implemented previously.
Penerapan Algoritma Naïve Bayes Untuk Analisa Kualitas Unit Body Mobil Pada Pt. Hyundai Motor Manufacturing Indonesia Andri Firmansyah; Fajrul Hamam
Prosiding Sains dan Teknologi Vol. 4 No. 1 (2025): Seminar Nasional Sains dan Teknologi (SAINTEK) ke 4 - Februari 2025
Publisher : DPPM Universitas Pelita Bangsa

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

Abstract

This study analyzes the quality of car body units using data mining classification with the Naive Bayes algorithm. The problem addressed is the high potential for defects in production processes, which requires an effective analytical method to classify body unit quality accurately. The objective of this research is to determine whether the Naive Bayes classification technique can be applied to assess car body unit quality and to evaluate its performance through accuracy, precision, and recall metrics. The research follows standard data mining stages, including data preparation, processing, and classification. Data processing and model testing were conducted using the RapidMiner tool. Several data split scenarios were applied to measure performance improvements based on the amount of data used. The results show that model performance increases as more data is processed. For data proportions of 70%, 80%, and 90%, the accuracy levels achieved were 99.62%, 99.66%, and 99.70%, respectively. Similarly, precision and recall values also improved with larger datasets. Based on these findings, it can be concluded that the Naive Bayes algorithm is effective for classifying car body unit quality and can support quality control processes in automotive manufacturing.
Implementasi Convolutional Neural Network untuk Klasifikasi Rambu-Rambu Lalu Lintas Andri Firmansyah; Kostaman
Prosiding Sains dan Teknologi Vol. 4 No. 1 (2025): Seminar Nasional Sains dan Teknologi (SAINTEK) ke 4 - Februari 2025
Publisher : DPPM Universitas Pelita Bangsa

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

Abstract

Traffic Sign Recognition (TSR) technology, which is commonly used for recognizing traffic signs through image processing, can be applied to driver assistance systems, advanced driver assistance systems, autonomous driving systems, road safety, urban environment recognizing, and traffic sign monitoring for maintenance purposes. The dataset used in this study consists of 34,799 traffic sign images categorized into 43 classes. The CNN model consists of two 5x5 convolutional layers, two 3x3 convolutional layers, two 2x2 Maxpool layers, and one fully-connected layer that utilizes the Softmax activation function. The number of filters used in each convolutional layer is 60. By using 22,271 training images, 50 epochs, the obtained error and accuracy values during the training stage are 0.0283 and 99.36%, respectively. In the testing stage with 75 epochs, the CNN model was able to obtain an error value of 0.0400 and an accuracy value of 98.76%.