This research evaluates the performance of several Faster R-CNN models with different hyperparameter configurations for brain tumor detection tasks. Evaluation results show that Model with a learning rate of 0.01, batch size of 4, Resnet50 backbone, and a dataset ratio of 80:20, achieved the best results. This model achieved mAP at IoU thresholds of 0.3, 0.4, and 0.5 of 0.9503, 0.9377, and 0.89…
The air quality in a region significantly impacts the health of its residents. The Indonesian government has established the Air Quality Index (AQI) as a parameter to assess air quality and its effects on the health of individuals exposed to the air for several hours to several days. Several studies have found that machine learning methods, particularly the Random Forest algorithm, can be used …
Pengolahan dokumen tekstual sering kali membutuhkan identifikasi informasi penting seperti nama orang, tempat, dan lembaga, namun proses manual memakan waktu dan kurang efisien. Named Entity Recognition (NER) menjadi solusi otomatis untuk tugas ini, tetapi penerapannya dalam bahasa Indonesia menghadapi tantangan seperti variasi dialek dan struktur linguistik yang kompleks. Penelitian ini menggu…
The rapid development of information technology has led to various innovations that simplify human activities, including the search for information through intelligent search engines such as Google, Bing, and Yahoo. However, the abundance of information available on the internet, especially related to tourism, often makes it difficult for users to find accurate and reliable information. Therefo…
X (Twitter), with 237.8 million daily active users mostly aged 18 to 29, has become one of the largest and most influential communication platforms in the world. However, despite its potential as a tool for information sharing and interaction, X (Twitter) also presents major challenges in terms of online behavior. One of the main problems that has emerged is the rise of hate speech, which can d…
As music genres diversify and online music libraries grow, the need for automated, accurate genre classification has become essential for efficient music organization and recommendation. In this research, we developed a music genre classifier using a custom Convolutional Neural Network (CNN) trained on mel-spectrogram images derived from the GTZAN dataset. The GTZAN dataset is a widely used ben…
DANA is an Indonesian financial technology company that provides infrastructure to support digital wallets in the modern era. With the DANA app, users can store money and make payments without using cash or cards, both for online and offline transactions, with speed, convenience, and guaranteed security. Although offering various conveniences, the DANA app still receives a variety of reviews fr…
Paraphrase generation is a part of text generation or Natural Language Generation (NLG) that aims to create paraphrased sentences with a different words or structure from the input sentence without altering its original meaning. This research builds a paraphrase generation system using the Transformer method. The results of the study indicate that the paraphrase generation model was successfull…
Object detection is the process of identifying and localizing a specific object in an image or video that aims to recognize the presence and position of the object specifically. This technology has various applications in daily life, such as face detection to open smartphones. However, a major challenge in object detection is the camera's sensitivity to light intensity. In low lighting conditio…
The rapid growth of social media interactions in Indonesia has generated a massive volume of text data containing diverse emotional expressions. The linguistic complexity and contextual richness of the Indonesian language make emotion identification and classification a challenging task. To address this issue, this study develops a multi-label emotion classification system by applying fine-tuni…
The rapid growth of digital content makes online news management increasingly challenging, as vast document streams demand compact representations of core information. Keyphrases provide concise lexical surrogates for main topics and support indexing, retrieval, and summarization, yet limited annotations motivate automatic systems that can predict both present and absent keyphrases. This study …
Player character requires a user to control its movements. The automation of a player character aims to create an agent capable of replacing the user. Deep Q-Learning (DQL) is one of the reinforcement learning algorithms commonly employed for automating player characters. This study implements the automation of a player character while introducing random obstacles into the game environment. The…
Short text messages, such as those found on social media and messaging platforms, often reflect the emotional expressions of users. Emotion clasification in these texts has significant potential for applications such as sentiment analysis and content personalization. This study aims to develop a short text emotion clasification model using the Long Short-Term Memory (LSTM) method. The dataset u…
Pempek Mamika still uses a manual sales system, which presents challenges in managing orders, inventory, and reporting. This research aims to design a website- based sales application using the Waterfall method, through the stages of needs analysis, design, implementation, and testing. The application provides registration, product catalog, shopping cart, order management, and sales reporting f…
UP 3 PT PLN (PERSERO) Palembang is one of the branches of PT. PLN located in South Sumatra. Currently, the processing of news portal data often encounters several issues, such as difficulties in presenting data reports. This results in inefficient reporting, as data processing is still performed manually and is not supported by an integrated information system to assist in generating news porta…
The distribution of goods in the food and beverage industry often faces challenges related to vehicle capacity limitations and customer time windows. This issue can be modeled as a Vehicle Routing Problem with Time Windows (VRPTW). To obtain an efficient solution, this study proposes a hybrid approach by combining the Nearest Neighbor (NN) heuristic for initial solution construction and the Fir…
The rapid development of information technology has driven business transformation from conventional sales systems to digital platforms, including at Emy Collection Boutique in Palembang, which still relies on manual transactions, resulting in limitations in data recording, market reach, and customer service. This study aims to design and develop a web-based digital sales application using the …
Indonesia, with its high biodiversity, is home to 1,539 bird species, some of which have morphological similarities that make manual identification challenging.This research aims to develop a bird species classification model in Indonesia using a Convolutional Neural Network (CNN) with the EfficientNet-B0 architecture to improve identification accuracy and speed. The model was trained using 10 …
CV Anisa is a company engaged in providing cleaning service solutions. In managing its inventory data, the company still relies on manual recording, which is prone to errors in both documentation and stock calculation. Such conditions may hinder operational activities, particularly when sudden shortages of supplies occur. To address these issues, this study aims to design and develop a web-base…
The design and development of a Web-Based Student Violation Application aims to assist schools in recording, managing, and monitoring student violation data more efficiently. The system was developed using the PHP programming language with a MySQL database and adopts the Waterfall development model as a systematic approach in the software design process. The implementation results show that the…
Facial images captured under low-light conditions often suffer from visual degradation, including low contrast, inadequate brightness, and loss of important details, which negatively impact face detection accuracy. This study aims to enhance the quality of low-light images using the Retinex method as a preprocessing step and to evaluate its effect on the performance of the YOLOv5 face detection…
The final project is a critical component of higher education, particularly in computer science and informatics, which continues to evolve rapidly, influencing the direction of academic research. This study aims to classify the trends in final project topics among students of the Informatics Engineering Program at Universitas Sriwijaya during the 2019–2023 period using the Latent Dirichlet Al…
The Education Development Contribution (SPP) payment system at SMA Negeri 2 Sungai Lilin currently uses a manual system for recording and managing student tuition payments. This method is considered inefficient due to the risk of recording errors, processing delays, and the lack of a centralized system to facilitate payment data tracking. This research was conducted to design a website-based tu…
SMA Negeri 2 Sungai Lilin masih mengelola perpustakaan secara manual, yang menyebabkan pencatatan data kurang efisien, proses peminjaman lambat, dan akses informasi terbatas. Penelitian ini bertujuan merancang sistem perpustakaan digital berbasis website menggunakan metode Rapid Application Development (RAD). Metode ini dipilih karena pendekatan iteratif dan keterlibatan pengguna yang tinggi, m…
Educational games require an adaptive assistance level system to adjust the level of help provided according to the player's ability. This study aims to develop an adaptive assistance level system based on fuzzy logic using the Mamdani and Sugeno methods, with inputs including stars, completion, and time. The system was implemented using the Python programming language and tested with 1,000 sim…
Penelitian ini membahas mengenai game edukasi pemograman dengan bantuan adaptif. Game ini memiliki puzzle yang harus di selesaikan dengan memasukkan algoritma yang tepat. Demi memunculkan bantuan yang ccok dengan pemain dibutuhkan algoritma FUZZY LOGIC untuk menentukan bantuan mana yang akan di keluarkan. Pengujian yang dilakukan pada penelitian ini merupakan pengujian untuk mendapatkan data ke…
Information system is a system that provides information for management in making decisions and also to run the operation of pharmacy clinics, where the system is a combination of people, information technology and organized procedures. In the service of pharmacy information system is one of the supports in processing pharmacy service data, one of which is taking drugs that have been prescribed…
The rapid development of information technology has a positive impact on data management, including the inventory process. At SMA Al Amalul Khair, inventory recording is still done manually, which is risky for recording errors and is less efficient. This study aims to design and build a web-based inventory application. This application is built using the PHP programming language, MySQL database…
This research aims to develop and implement a real-time multi-face detection and emotion recognition system. The Haar Cascade method is used in the face detection stage to identify the position of faces in the image, while the Convolutional Neural Network (CNN) is used in the emotion classification stage based on the detected faces. The datasets used include FDDB for face detection testing and …
ChatGPT has become one of the most popular artificial intelligence tools worldwide, but its rapid adoption has also generated diverse user reactions and reviews. Understanding these perceptions is important for evaluating and improving service quality. Sentiment analysis is a suitable approach to explore such opinions. This study employs BERT (Bidirectional Encoder Representations from Transfor…