WEB-BASED ASSET TRANSFER INVENTORY MANAGEMENT INFORMATION SYSTEM AT THE MARINE AFFAIRS AND FISHERIES SERVICE OF SOUTH SUMATRA PROVINCE
Karakter non-pemain (NPC) pada game fighting 2D umumnya masih menggunakan scripted AI yang statis, sehingga mengurangi dinamika tantangan bermain. Oleh karena itu, penelitian ini bertujuan mengimplementasikan algoritma Proximal Policy Optimization (PPO) berbasis Deep Reinforcement Learning guna mengembangkan agent musuh yang adaptif. Simulasi dibangun menggunakan Unity Engine dan ML-Agents Tool…
Helminthiasis is classified by the World Health Organization (WHO) as one of the Neglected Tropical Diseases (NTDs) due to its wide distribution, yet it often remains a low priority in global health agendas. Control efforts for helminthiasis are generally carried out through manual microscopic examination. However, this method requires specialized expertise, has technical limitations such as lo…
Asset management and maintenance at the Department of Marine Affairs and Fisheries of South Sumatra Province are still carried out manually, causing difficulties in asset monitoring and maintenance scheduling. This study aims to develop a Web-Based Asset Maintenance Management Information System with preventive and corrective scheduling. The system was developed using the Waterfall method, UML,…
The evaluation of academic services in the Information Management Study Program at Sriwijaya University is not yet available on a single integrated platform. This study designed and developed a Mobile-Based Academic Service Evaluation Application using the Prototype method with React Native , Expo, TypeScript, and PostgreSQL technologies. The application includes features for evaluating faculty…
Sistem pengelolaan inventarisasi data aset pada Dinas Kelautan dan Perikanan Provinsi Sumatera Selatan saat ini belum terintegrasi secara optimal. Seluruh data inventaris yang tergabung menjadi satu kesatuan besar tanpa kategorisasi yang sistematis menyulitkan proses pemantauan kondisi kelayakan barang, pelacakan riwayat perawatan, serta penyusunan laporan periodik. Penelitian ini bertujuan unt…
Student attendance is an important activity in supporting school administration and monitoring student presence. SMP Negeri 30 Palembang still uses a manual attendance system that is less effective. The recording and recapitulation processes take time and are prone to errors This study aims to design and implement a web-based student attendance application, The system uses barcode technology to…
Indonesia, as an archipelagic country, is highly dependent on air transportation to support interregional connectivity. Airports play a role in supporting mobility, economic activities, and equitable development. This study aims to cluster airports in Indonesia based on domestic air traffic activity using the K-Means algorithm and to analyze the characteristics and patterns of the clusters. The…
PT Lematang Coal Lestari does not yet have an AI-based company profile application, making it difficult to access company information quickly and interactively. This research aims to design and develop an AI-based company profile application that facilitates the accurate and responsive delivery of company information.The application development uses the waterfall method, with PHP as the program…
Indonesia’s rapidly expanding beverage industry demands efficient training methods for workers who must prepare drinks accurately under pressure. Traditional training often faces high costs, limited resources, and reliance on instructors, making it less accessible. This study introduces a Virtual Reality (VR) simulation developed with Unity to provide an immersive, cost-effective training alt…
Manual analysis of COVID-19 chest CT scans is often time-consuming and prone to subjectivity, thereby hindering diagnostic efficiency. Therefore, this study aims to develop an automatic segmentation system using a Custom U-Net architecture with a pre-trained DenseNet-169 encoder to accurately map infection areas, including Ground Glass Opacity (GGO), Consolidation, and Pleural Effusion classes.…
The development of text processing technology allows for automated data classification using machine learning methods. In the case classification process, manual text grouping is often time-consuming and error-prone. This study aims to build a text classification system capable of automatically grouping case descriptions into specific categories. The methods used in this study are Support Vecto…
Information systems in the Faculty of Computer Science, Sriwijaya University generally have separate authentication and user management mechanisms in each application. This condition causes repeated login processes, decentralized role management, and less efficient application integration. This research aims to develop a role-based Single Sign-On (SSO) system as a centralized authentication and…
The Faculty of Computer Science at Sriwijaya University regularly accommodates students from various schools to conduct internship programs. However, the monitoring process regarding attendance, daily activity progress, and evaluations has still been carried out manually. This conventional approach results in difficult data management, risks of physical document loss, and a lack of time efficie…
The Department of Education and Culture of Muara Enim Regency still manages archives manually, including recording, disposition, and document storage processes. This condition causes slow document retrieval, ineffective monitoring, and risks of archive loss or damage. This study aims to design and develop a web-based digital archive application to support the management of incoming and outgoing…
Rapid and reliable pathological evaluation is made possible in large part by the automatic detection of liver histological abnormalities. Using YOLOv11 on the Roboflow Liver Disease public dataset, this work aims to maximize precision in the detection of four lesions: ballooning, fibrosis, inflammation, and steatosis. After pre-processing the data with a 640×640 resize, the model was trained u…
erkembangan pesat kecerdasan buatan, khususnya dalam model generatif, telah membuka peluang besar bagi otomatisasi dalam industri pengembangan game. Namun, pengembang indie dan studio kecil masih menghadapi kendala signifikan dalam pembuatan aset game 2D, terutama sprite sheet karakter, yang secara tradisional memerlukan waktu lama, biaya tinggi, dan upaya manual untuk menghasilkan berbagai sud…
The self-attention mechanism in Large Language Models (LLMs) is computationally intensive and memory-bound, posing significant challenges for inference on consumer-grade hardware. This research proposes a memory-aware optimization of CUDA kernels for the self-attention mechanism within the GPT-2 architecture, integrating Shared Memory Tiling, Streaming Softmax, and Kernel Fusion to minimize glo…
The number of outpatient visits in hospitals often fluctuates, making it difficult for hospital management to plan administrative services, particularly in managing patient queues, as well as the allocation of resources, especially administrative staff, effectively. Therefore, a prediction method is needed to estimate the number of patient visits in the future. This study aims to apply and comp…
This study aims to develop a pneumonia classification model on chest X-ray images using a Convolutional Neural Network with the DenseNet-121 architecture for early detection of lung diseases. The dataset consists of 5,856 images divided into training, validation, and testing sets. The research stages include preprocessing, image augmentation, model training using a progressive fine-tuning strat…
This study implements and compares the performance of the IndoBERT deep learning model in analyzing the sentiment of Gojek application reviews using 3-class and 5-class schemes. Data was extracted via web scraping, yielding 66,709 raw reviews, which were then preprocessed and balanced into 23,115 (3-class) and 32,899 (5-class) datasets. Training was executed with an 80:10:10 ratio across six sc…
The rapid growth of social media has enabled the misuse of comment sections as a medium for promoting online gambling. The high volume of comments makes manual moderation ineffective, thus requiring an automated classification system. This study aims to develop a classification system for online gambling comments using the IndoBERT model and to evaluate its performance based on accuracy, precis…
DANA has become one of the most popular e-wallet applications in Indonesia. This development has elicited various reactions and responses from users in the form of reviews. These reviews can provide important insights for improving the quality of the application's services. This study aims to conduct sentiment analysis on user reviews by utilizing Long Short-Term Memory (LSTM) as the model arch…
Phishing is a form of cyberattack that exploits fraudulent websites to obtain users’ sensitive information. This study aims to compare the performance of the XGBoost machine learning algorithm and CNN 1D deep learning in detecting phishing URLs using tabular URL data. XGBoost was chosen because it is effective in handling tabular data and capable of modeling nonlinear relationships among feat…
Alzheimer’s disease is a progressive neurodegenerative disorder that is the leading cause of dementia. The use of Magnetic Resonance Imaging (MRI) in ResNet18-based classification can be hindered by the presence of noise, particularly Rician noise, which obscures important structural details and reduces model performance. This study employs the Nonlinear Activation Free Network (NAFNet) to im…
Fluctutations in daily visitor numbers at Kampung Radja Jambi present challanges for optimal operation planning. This study aims to compare the performance of the Fuzzy Time Series (FTS) Cheng and FTS Lee methods in forecasting daily visitor number using secondary data from Januari 1, 2024 to December 31, 2025. After preprocessing, 648 observations were analyzed using FTS approach, and forecast…
One of the main challenges in English to Javanese machine translation is the model's difficulty in capturing contextual relationships between words, especially in complex sentences. Without an Attention Mechanism, the model tends to be unable to focus on the relevant parts of the source sentence during the translation process. This study aims to develop a Neural Machine Translation (NMT) model …
Penelitian ini bertujuan menganalisis hubungan kausalitas antara indeks kebahagiaan, pengeluaran pemerintah, dan pertumbuhan ekonomi di 12 negara emerging market selama periode 2013–2024. Data yang digunakan merupakan data sekunder yang diperoleh dari World Happiness Report dan World Bank. Metode analisis yang digunakan adalah Panel Vector Autoregression (PVAR) dengan uji kausalitas Granger u…
The Seleksi Penerimaan Murid Baru (SPMB) through the Tes Kemampuan Akademik (TKA) pathway for senior high schools in Palembang is a competitive process that creates uncertainty in determining students’ admission chances. This study aims to develop a prediction model for student admission using a machine learning approach based on ensemble learning stacking. The dataset consists of 4,952 appli…
School selection at the senior high school level is an important decision amid intense competition in the student admission process and multiple influencing factors such as academic performance, domicile, and school capacity. This study aims to develop a recommendation system based on stacking ensemble learning that combines Random Forest and XGBoost as base learners, with Logistic Regression a…