cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Hafiz Irsyad
Contact Email
hafizirsyad@mdp.ac.id
Phone
+6281373740969
Journal Mail Official
hafizirsyad@mdp.ac.id
Editorial Address
Jl. Rajawali No.14, 9 Ilir, Kec. Ilir Tim. II, Kota Palembang, Sumatera Selatan 30113
Location
Kota palembang,
Sumatera selatan
INDONESIA
MDP Student Conference
Published by Universitas Multi Data Palembang
ISSN : -     EISSN : -     DOI : https://doi.org/10.35957/mdp-sc.v2i1.3997
Core Subject : Economy, Science, Engineering,
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering
MDP Student Conference is a one-year national conference organized by the Universitas Multi Data Palembang. We are inviting teachers, lecturers, researchers, scholars, students, and or other key stakeholders to present and discuss their latest findings, innovations, and best practices as well as fresh ideas on, but not limited to, the listed sub-themes.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 73 Documents
 1   2   3   4   5 
Search results for , issue "Vol 5 No 2 (2026): The 5th MDP Student Conference 2026" : 73 Documents clear
Klasifikasi Multikelas Varietas Kacang Kering Menggunakan Metode Hybrid SVM Berbasis DAG Nababan, Dinda; Nadeak, Christyan Tamaro; Rassiyanti, Linda; Farid, Fajri
MDP Student Conference Vol 5 No 2 (2026): The 5th MDP Student Conference 2026
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/mdp-sc.v5i2.14094

Abstract

This study analyzes the performance of three conventional SVM strategies, namely One-vs-One (OvO), One-vs-Rest (OvR), and Directed Acyclic Graph OvO (DAG-OvO), compared with the hybrid approach Directed Acyclic Graph Rest-vs-Rest (DAG-RvR) in the context of multiclass classification using the Dry Bean Dataset. All models are evaluated based on accuracy and macro metrics to measure the consistency of predictions between classes. The results show that both conventional and hybrid methods achieve the same high level of accuracy, namely 0.92, with Precision, Recall, and F1-score Macro values ​​that were also identical between approaches. The main difference between the approaches lies in computational efficiency. OvO and DAG-OvO show the fastest training time, while DAG-RvR is the most efficient method in the inference stage. These findings confirm that the hybrid DAG-RvR structure can accelerate the prediction process without compromising accuracy, making it worthy of consideration for applications that require fast inference.
Klasifikasi Multikelas Support Vector Machine dengan Hibrida Directed Acyclic Graph One Vs One dan Rest Vs Rest pada Klasifikasi Tingkat Obesitas Naufal, Daffa Ahmad; Nadeak, Christyan Tamaro; Rassiyanti, Linda; Farid, Fajri
MDP Student Conference Vol 5 No 2 (2026): The 5th MDP Student Conference 2026
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/mdp-sc.v5i2.14097

Abstract

This research is focused on analyzing how well different multiclass Support Vector Machine (SVM) classification methods can predict obesity levels. It also presents a new hybrid Directed Acyclic Graph Rest-vs-Rest (DAG-RvR) method as a better option. The study utilizes a dataset called the Obesity Risk Prediction Cleaned, which has information on seven different obesity categories. The methods being assessed include One-vs-One (OvO), One-vs-Rest (OvR), DAG-One-vs-One (DAG-OvO), and the new DAG-RvR method. For fine-tuning the parameters, GridSearchCV and the RBF kernel were used. The findings reveal that DAG-RvR achieves an accuracy of 0.91, which is similar to OvO and DAG-OvO, but it trains much quicker, taking just 0.3422 seconds. Even though its precision, recall, and F1-score are a bit lower than the pairwise methods, DAG-RvR still maintains reliable multiclass performance. In summary, this method strikes a good balance between achieving high accuracy and being efficient in computations.
Klasifikasi Varietas Beras Menggunakan Hybrid SVM Berbasis DAG–OVO dan RVR Leander, Marleta Cornelia; Nadeak, Christyan Tamaro; Rassiyanti, Linda; Farid, Fajri
MDP Student Conference Vol 5 No 2 (2026): The 5th MDP Student Conference 2026
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/mdp-sc.v5i2.14108

Abstract

This research proposes a hybrid Support Vector Machine (SVM) strategy for multiclass rice variety classification by combining Directed Acyclic Graph Rest-vs-Rest (DAG-RvR) with K-Means clustering. Five rice varieties were analyzed using 16 morphological and texture features extracted from the Rice Image Dataset. Three conventional SVM methods—One-vs-One (OvO), One-vs-Rest (OvR), and DAG-OvO—were evaluated as baselines. Two hybrid schemes were then developed: DAG-RvR K-Means–OvO and DAG-RvR K-Means–K-Means. Experimental results show that all methods achieve high accuracy of approximately 99%, indicating strong feature separability among rice varieties. However, the proposed DAG-RvR K-Means–OvO provides the most efficient performance, achieving the fastest training time while maintaining competitive testing speed and the highest accuracy of 0.99040. The findings demonstrate that integrating K-Means–based class partitioning with pairwise SVM classification improves computational efficiency without reducing predictive performance, making the hybrid approach suitable for fast and accurate multiclass classification tasks.
Perancangan Website Tiket Online Bird Park Palembang Menggunakan Design Thinking Angel, Stevany; Sean, Obert; Engelica, Noviana; Hafildah, Nora
MDP Student Conference Vol 5 No 2 (2026): The 5th MDP Student Conference 2026
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/mdp-sc.v5i2.14263

Abstract

This research aims to design the official website of Palembang Bird Park as an information medium and online ticket booking platform. Palembang Bird Park, located in the Jakabaring area, has significant tourism potential with a collection of over 1,000 birds from various species. However, the conventional information and ticket booking system has become an obstacle in tourism development. This research applies the Design Thinking method, which includes the stages of Empathize, Define, Ideate, Prototype, and Test, to produce a user-centered design. The result is a website prototype with features including destination information, gallery, ticket prices, online ticket booking, and integrated payment system. Testing using the Black Box Testing method shows that all features function properly, with a success rate of 100%.
Pengembangan Aplikasi Manajemen Stok Berbasis RUP pada PT Anugerah Pelangi Nusantara Amelia, Siska; Febryan, Migel Orvin; Wijaya, Novan
MDP Student Conference Vol 5 No 2 (2026): The 5th MDP Student Conference 2026
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/mdp-sc.v5i2.14351

Abstract

A mobile-based inventory management application was developed for PT Anugerah Pelangi Nusantara to improve the accuracy and efficiency of stock management processes. The scope includes system analysis, design, implementation, and testing of an application that manages item data, stock-in and stock-out transactions, and inventory reports. The Rational Unified Process (RUP) methodology was applied through the inception, elaboration, construction, and transition phases. System modeling utilized Unified Modeling Language diagrams, while functional testing employed the black box testing method. The results indicate that the application successfully automates inventory recording, updates stock data in real time, and generates accurate inventory reports. All core system functions operated as expected during testing. Overall, the developed application reduces manual recording errors, accelerates reporting processes, and supports more efficient inventory control within the company.
Smart Water Tank Management System Berbasis IoT dan WebSocket untuk Kontrol Dua Pompa Otomatis Trisaptono, Raymondus; Marpaung, Bryant Valencio; Sumual, Willyam Lucas Haposan; Widiyanto, Eka Puji
MDP Student Conference Vol 5 No 2 (2026): The 5th MDP Student Conference 2026
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/mdp-sc.v5i2.14389

Abstract

Water management in multi-story buildings requires efficiency to prevent resource wastage. At the Santo Paulus Plaju Catholic Church, manual pump operation frequently leads to tank overflows, water shortages, and potential pump damage due to dry-running. This study designs a centralized automatic control system for filling and booster pumps using an ESP32 microcontroller and Websocket protocol for real-time monitoring. The system integrates an AJ-SR04M ultrasonic sensor for level measurement and a YF-S201 flowmeter for discharge detection. Testing results demonstrate system successfully automates operations based on hysteresis logic (ON <25%, OFF >90%) and flow detection (>4.0 L/m). Furthermore, the Websocket-based interface achieves data update latency under 1 seconds, ensuring a responsive and transparent management solution.
Sistem Deteksi Masker Wajah Menggunakan CNN untuk Akses Pintu Otomatis Firizki, Muh.; Brilliant, Brian; Warohma, Ayu Mawadda
MDP Student Conference Vol 5 No 2 (2026): The 5th MDP Student Conference 2026
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/mdp-sc.v5i2.14413

Abstract

This research discusses the development of a face mask detection system using a Convolutional Neural Network (CNN) for automatic door access in hospitals. Considering the high risk of infectious disease transmission in hospital environments, the implementation of strict health protocols, including mandatory mask usage, is essential. Manual supervision of mask compliance has limitations; therefore, an automated system is required to improve monitoring effectiveness. The dataset used in this study was collected using an ESP32 Cam, consisting of 1,186 images of masked and unmasked faces. The CNN model achieved an average training accuracy of 96.60%, with Precision and Recall values of 0.98. The automatic door system was evaluated through real-time testing involving six subjects, each undergoing 15 trials with masks and 15 trials without masks, resulting in a total of 180 trials. The system achieved a detection accuracy of 90.00% for masked faces and 74.44% for unmasked faces, with an overall system accuracy of 82.22%. These results indicate that the proposed system is capable of reliably supporting automatic door access control based on face mask compliance in hospital environments.
Sistem Deteksi dan Pencatatan Akses Perpustakaan Menggunakan Sensor Gerak IoT dengan Visualisasi Data Berbasis Website Panjaitan, Febriyanti; Hermantan, Jehuda Rapha Putra; Effendy, Leon Duta; Kinton, Frederick
MDP Student Conference Vol 5 No 2 (2026): The 5th MDP Student Conference 2026
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/mdp-sc.v5i2.14433

Abstract

This study aims to develop a prototype of an Internet of Things (IoT)–based people counting system for real-time room occupancy monitoring. The scope of the research is limited to the design and implementation of a physical prototype and data visualization through a web dashboard, without involving individual identification. The research employs an experimental and system development (Research and Development) method using infrared sensors, Arduino Uno, ESP32, and a servo motor. The system is designed to detect entry and exit activities, count the number of people, and transmit data to a server via a Wi-Fi network to be displayed on a web dashboard. The results show that the system operates as designed, performing automatic counting and presenting real-time occupancy information. In conclusion, the developed IoT system can serve as an initial solution for room occupancy monitoring and has the potential to be further developed through the integration of face recognition technology
Penerapan metode RUP dalam pengembangan website booking pada Hotel Sriwidjaya Palembang Az Zahrah, Siti Fatimah; Veraldo, Veraldo; Wijaya, Novan
MDP Student Conference Vol 5 No 2 (2026): The 5th MDP Student Conference 2026
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/mdp-sc.v5i2.14474

Abstract

The development of information technology encourages hotels to improve their reservation services through digital platforms. Hotel Sriwidjaya Palembang still applies a manual booking process that may cause data inaccuracies and inefficiencies in service delivery. This research aims to implement the RUP (Rational Unified Process) method in developing a web-based hotel booking website to support online reservations and reservation management. The research scope focuses on the system development stages consisting of Inception, Elaboration, Construction, and Transition. The website is developed with features such as room availability information, online booking, and reservation management. The result show that the implementation of the RUP method can produce a structured and functional hotel booking website that improves reservation accuracy and service efficiency. In conclusion, the developed website is expected to assist Hotel Sriwidjaya in managing reservations more effectively and providing better services to customers.
Digitalisasi Sistem Absensi dan Informasi Karyawan di Perusahaan BJIB Johan, Femmy; Verty, Jennifer; Wijaya, Novan
MDP Student Conference Vol 5 No 2 (2026): The 5th MDP Student Conference 2026
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/mdp-sc.v5i2.14475

Abstract

BJIB still uses manual attendance, which can lead to potential recording errors, delays in recapitulation, and a lack of transparency in attendance data. This study aims to design and build a mobile-based employee service application that supports digital attendance using QR Codes and provides information in the form of employee data and attendance history. This study uses the waterfall method, which includes needs analysis, interface design, implementation using Laravel and MySQL, testing, and maintenance. Testing was carried out on the login feature, attendance entry and exit, and history display. The results of the study show that all features run well and are able to record attendance accurately and present data in real-time. This system improves administrative efficiency, reduces human error, and accelerates the recapitulation process. Thus, the developed application can be an effective solution for BJIB in supporting the digitalization of employee data management.

Page 1 of 8 | Total Record : 73

 1   2   3   4   5 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue Vol 5 No 2 (2026): The 5th MDP Student Conference 2026 Vol 5 No 1 (2026): The 5th MDP Student Conference 2026 Vol 4 No 2 (2025): The 4th MDP Student Conference 2025 Vol 4 No 1 (2025): The 4th MDP Student Conference 2025 Vol 3 No 2 (2024): The 3rd MDP Student Conference 2024 Vol 3 No 1 (2024): The 3rd MDP Student Conference 2024 Vol 2 No 2 (2023): The 2nd MDP Student Conference 2023 Vol 2 No 1 (2023): The 2nd MDP Student Conference 2023 Vol 1 No 1 (2022): The 1st MDP Student Conference 2022