CLUSTERING MENGGUNAKAN METODE K-MEDOIDS PADA ARTIKEL BERITA ONLINE BERBAHASA …

The rapid growth of Indonesian online news articles presents challenges in clustering based on content similarity. This study aims to develop a clustering system for online news articles using the k-medoids method. A total of 500 articles from Kaggle were processed through text preprocessing (case folding, tokenizing, stopword removal, and stemming), TF-IDF weighting, and clustering with k-medo…

PENCARIAN BAKAT (TALENT SCOUTINGI) RENANG PADA ANAK MENGGUNAKAN ALGORITMA K-N…

Swimming requires an objective and efficient talent identification system. This study develops a machine learning-based system using the K-Nearest Neighbors (KNN) algorithm to predict young athletes' potential based on anthropometric and motor skill data. The dataset consists of 50 normalized samples evaluated through K-Fold Cross Validation (K=5 and 10). Test results show the optimal configura…

OPTIMASI ALGORITMA NAIVE BAYES DENGAN PARTICLE SWARM OPTIMIZATION UNTUK MENIN…

Water quality is a fundamental aspect of life, particularly in regions that rely on rivers as the primary source of raw water. However, anthropogenic activities such as industrial, agricultural, and domestic processes have contributed to increasing water pollution, while the demand for clean water continues to rise in line with population growth. This study aims to develop a water quality class…

KLASIFIKASI JENIS GANGGUAN TIDUR MENGGUNAKAN METODE LONG SHORT TERM MEMORY (L…

Sleep quality plays a critical role in maintaining physical, mental, and emotional wellbeing. Early detection of sleep disorders such as insomnia and sleep apnea is essential for enabling more effective clinical interventions. This study investigates the optimization of sleep disorder classification using Long Short-Term Memory (LSTM) networks based on time-series data incorporating 13 physiolo…

PENGEMBANGAN ALAT DETEKSI API PADA KEBAKARAN BERBASIS KAMERA DAN SENSOR GPS S…

Fires are unexpected events that often occur in daily life, causing significant threats and losses to the public. Early fire detection plays a crucial role in disaster mitigation and environmental protection efforts, especially in areas prone to fire incidents such as forests and open lands. Delays in detecting the presence of fire can lead to wider and harder-to-control spread. Therefore, a sy…

PENGEMBANGAN GAME DOODLE DENGAN PENILAIAN GAMBAR OTOMATIS MENGGUNAKAN MODEL CNN

In the era of artificial intelligence (AI) development, the integration of machine learning technology in games continues to advance. This study aims to develop a Convolutional Neural Network (CNN) model that functions as an automatic evaluation agent for doodle images in a drawing game. The CNN model is trained using the Google Quick Draw dataset to recognize images created by players. Evaluat…

KLASIFIKASI LEVEL ROASTING PADA BIJI KOPI MENGGUNAKAN ALGORITMA CONVOLUTIONAL…

Coffee roasting is the process of roasting coffee beans to bring out the aromas and flavors locked inside the beans. Roasted coffee beans are initially green in color which is then roasted in a certain temperature and time which causes the color to change to brown. This research aims to classify the roasting level of coffee beans using convolutional neural network (CNN) algorithm with ResNet50V…

DETEKSI KEBAKARAN BERDASARKAN VIDEO MENGGUNAKAN MASK R-CNN

Fire is one of the disasters that can cause great losses, both in terms of loss of life and economic loss. Fast and accurate fire detection is the main key to prevent fires from getting bigger and out of control. This study aims to develop a fire detection system using a video camera that can provide fire information as quickly as possible. This fire detection system uses Mask R-CNN model to de…

PREDIKSI WAKTU JASA SERVICE PT. GOBEL DHARMA NUSANTARA MENGGUNAKAN DECISION TREE

PT. Gobel Dharma Nusantara (GDN), a subsidiary of the Gobel Group providing service for Panasonic products, handles an average of 8,000 transactions per month. A prediction system is therefore necessary to help analyze this data effectively. This research aims to build a time prediction system using the Classification and Regression Tree (CART) algorithm to predict service patterns based on his…

PERBANDINGAN FUZZY INFERENCE SYSTEM TSUKAMOTO DAN MAMDANI DALAM MEMPREDIKSI T…

Stunting is a growth disorder in toddlers characterized by a height below the age-standard due to chronic nutritional deficiencies. This study aims to design and compare prediction models for stunting levels using two Fuzzy Inference System (FIS) methods: Tsukamoto and Mamdani. The data used comes from the secondary dataset "data set clustering gizi" obtained from Kaggle, consisting of 495 todd…

DETEKSI KATA KASAR DALAM LIRIK LAGU BERBAHASA INGGRIS MENGGUNAKAN MODEL BERT

Music plays a significant role through digital streaming platforms, while concerns about offensive language in lyrics, especially among young listeners, require attention. This study develops a BERT-based model to detect offensive language in English song lyrics. The dataset comprises 3,598 lyrics, divided into training 2,878 data, validation 360 data, and test 360 data. Experiments tested 12 p…

KLASIFIKASI CITRA KUE TRADISIONAL MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NET…

Traditional cake image classification aims to recognize various types of cakes based on visual features, thereby assisting in the effort to introduce traditional cakes. Indonesian traditional cakes hold significant cultural value that must be preserved while also presenting substantial potential in supporting tourism through culinary tourism. This study develops a classification model based on …

PENGEMBANGAN CHATBOT MENGGUNAKAN BERT UNTUK LAYANAN BANTUAN TERKAIT PRODUK APPLE

Edition

-

ISBN/ISSN

-

Collation

xviii, 68 hlm.; tab.; 29 cm.

Series Title

-

Call Number

T1734232025

OPTIMASI STRATEGI PEMILIHAN PEMAIN SEPAK BOLA PADA PRO EVOLUTION SOCCER 2017 …

This study aims to optimize the process of selecting football players in the PES 2017 game using genetic algorithms. The optimization is conducted to identify the best combination of players based on the average player ratings over a season, thereby maximizing team performance in the game. The methodology employed in this research is experimental, utilizing the application of genetic algorithms…

KLASIFIKASI UJARAN KEBENCIAN DI MEDIA SOSIAL APLIKASI X MENGGUNAKAN RANDOM FO…

Classification is one of the fields of Natural Language Processing that automates the classification of text into one or more appropriate categories based on its content by building a model using training data. This study aims to classify hate speech tweets on application X using Random Forest and Synthetic Minority Oversampling Technique (SMOTE). The Random Forest approach is used because of i…

KLASIFIKASI EMOSI PADA TEKS BERBAHASA INDONESIA DENGAN FINE-TUNING INDOBERT

The increasing use of social media has led to significant growth in Indonesian text data, creating complexity in emotion identification and classification tasks. To address this challenge, this study develops an emotion classification system using the fine-tuning method on the IndoBERT model. This research aims to classify emotions in Indonesian text using IndoBERT fine-tuning. The study utiliz…

PENGELOMPOKKAN ARTIKEL ILMIAH MENGGUNAKAN MULTIBERT DAN K-MEANS

The publication rate of scientific articles has significantly increased over time. This presents a challenge for journal administrators and academics in organizing and sorting these articles to align with the journal's scope. This study aims to address this issue by developing a scientific article clustering system utilizing MultiBERT as the data representation model and K-Means for cluster ide…

KEMIRIPAN SEMANTIK DOKUMEN TUGAS AKHIR TERHADAP ONTOLOGI BIDANG ILMU INFORMAT…

The increasing number of multidisciplinary undergraduate theses in Informatics field presents challenges in categorizing these documents accurately. This study develops a system to measure the semantic similarity of final project documents to the ontology of Informatics using the Wu Palmer method as a solution to this problem. This method utilizes ontology tree structures and taxonomic depth to…

KLASIFIKASI TUBERKULOSIS PADA CITRA CHEST X-RAY MENGGUNAKAN CONVOLUTIONAL NEU…

Tuberculosis is still one of the infectious diseases that causes high mortality rates worldwide. Early detection using Chest X-Ray images is very important in the effort to treat this disease. However, manual interpretation of X-ray results performed by doctors can cause differences in diagnosis. This study aims to classify tuberculosis in Chest X-Ray images by implementing three Convolutional …

TOPIC MODELLING DAN TOPIC GENERATION PADA REVIEW GAME STEAM DENGAN FINE-TUNIN…

This study aims to develop and evaluate a Topic Modelling and Topic Generation system using user review data from the Steam platform. The research utilizes the BERTopic model to cluster reviews into topics in an unsupervised manner, and the Qwen2.5 Large Language Model to generate more informative topic representations. Various algorithm combinations covering embedding, dimensionality reduction…

FINE-TUNING MODEL BERT UNTUK NAMED ENTITY RECOGNITION

A sentence can contain various named entities with important meanings, such as names of people, locations, organizations, and time expressions. However, extracting this information manually requires significant time and resources. Named Entity Recognition (NER) offers an automated solution that improves the efficiency of this task. One method for developing an NER system is by using BERT, a tra…

ANALISIS SENTIMEN TIKTOK SHOP PADA TWITTER MENGGUNAKAN METODE SUPPORT VECTOR …

TikTok Shop, as a social commerce feature in the TikTok application, has become a popular shopping platform in Indonesia. However, government regulations prohibiting direct transactions on social media forced TikTok to stop this service from October 4 until it reopened on December 12, 2023, after establishing a partnership with Tokopedia. This incident triggered various public opinions. This se…

PREDIKSI TINGKAT KRIMINALITAS MENGGUNAKAN LONG SHORT TERM MEMORY (LSTM)

Prediction or also called forecasting is the process of estimating events that will occur in the future. In this research, software is developed that can predict crime rates using the Long Short-term Memory method using the Los Angles crime dataset which has a crime type domain of 139 with details of 9 types of crimes that have the most frequency, namely; vehicle - stolen, battery - simple assa…

PERBANDINGAN METODE INFERENSI FUZZY MAMDANI DAN TSUKAMOTO DALAM MELAKUKAN PRE…

Kidney stones are one of the most common health problems and have the potential to cause chronic kidney failure if not properly addressed. To support early prevention efforts, this study aims to compare two fuzzy inference methods, namely Mamdani and Tsukamoto. The study will use 89 data points obtained from Kaggle under the title "Kidney Stones Dataset." In predicting the risk of kidney stones…

SISTEM PENDETEKSI KUALITAS FISIK PADA BIJI KOPI SECARA REALTIME MENGGUNAKAN M…

In this global era, the demand for coffee beans has been increasing year by year. The economic value of coffee beans is greatly influenced by the quality of the beans being marketed. Manual assessment of coffee quality by experts or farmers tends to be subjective and time-consuming. Based on these conditions, this study developed software to detect coffee bean quality in real-time using the YOL…

PERBANDINGAN DEEP LEARNING CNN DENSENET DENGAN TRANSFORMER PADA KLASIFIKASI C…

Klasifikasi citra makanan merupakan tantangan penting dalam computer vision dengan aplikasi luas pada sistem pencatatan gizi dan pelacakan kalori, namun penelitian yang secara langsung membandingkan arsitektur CNN dan Transformer pada dataset makanan multikelas dengan variasi visual tinggi masih terbatas. Penelitian ini membandingkan dua arsitektur deep learning, yaitu DenseNet121 dan Vision Tr…

PENERAPAN PARTICLE SWARM OPTIMIZATION UNTUK PROCEDURAL CONTENT GENERATION PAD…

The rice farming sector plays a strategic role in supporting national food security; however, its sustainability is under serious pressure due to the conversion of paddy fields into oil palm plantations. In Banyuasin Regency, the sustainability of rice farming has been increasingly threatened by this land-use conversion. The binary logistic regression analysis shows that farm income is the only…

INTERAKSI DIALOG NPC BERBASIS SPEECH RECOGNITION DAN FUZZY STRING MATCHING DE…

This study aims to develop an interactive dialogue system based on Speech Recognition in games, allowing players to interact with Non-Player Characters (NPCs) through real-time voice commands. The method used is Fuzzy String Matching with the Levenshtein Distance algorithm to calculate the similarity between speech-to-text conversion results and predefined system commands. The research stages i…

PENERAPAN HAND GESTURE RECOGNITION UNTUK KONTROL GAME MAZE MENGGUNAKAN YOLOV11

Advances in computer vision and artificial intelligence technology are driving innovation in human computer interaction, one example of which is Hand Gesture Recognition. In maze games, control systems generally still use conventional devices such as keyboards, mice, or joysticks, thus not providing a fully natural and interactive gaming experience. Therefore, this study implemented a Hand Gest…

KLASIFIKASI UJARAN KEBENCIAN BAHASA INDONESIA MENGGUNAKAN INDOBERT DAN CONVOL…

The increasing spread of hate speech on social media, particularly on Twitter (X), poses challenges for manual content moderation, which tends to be ineffective. This condition highlights the need for an automated classification system capable of accurately detecting hate speech. This study aims to develop a hate speech classification model using approach combining IndoBERT and Convolutional Ne…