Filter by
TRANSFORMASI ORIENTASI TEKS BALON PERCAKAPAN VERTIKAL PADA CITRA MANGA BERBAH…
Text in Japanese manga speech balloons is typically written vertically, whereas modern OCR technology is optimized for horizontal text. As a result, standard OCR engines like EasyOCR struggle to accurately read vertically oriented manga text. To address this issue, a method is proposed that uses character detection and text orientation transformation to improve OCR accuracy on vertical text. Sp…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xv, 104 hlm.; ilus.; tab.; 29 cm.
- Series Title
- -
- Call Number
- T1930522026
PERBAIKAN KUALITAS CITRA BAWAH AIR MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (…
Underwater images suffer from degradation caused by light refraction and suspended particles, resulting in the appearance of noise, color casts, low contrast, and loss of fine details, hindering further vision tasks like object detection. This study implements Residual U-Net Model, incorporating Residual blocks onto each convolutional block in the encoder side to improve feature extraction and …
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xiv, 103 hlm.; ilus.; tab.; 29 cm.
- Series Title
- -
- Call Number
- T1929542026
PENGARUH TEKNIK OVERSAMPLING DALAM KLASIFIKASI BAHASA DAERAH MENGGUNAKAN METO…
Regional language classification is one of the challenges in natural language processing due to the limited amount of data and the high lexical similarity among languages. This condition leads to data imbalance, particularly in minority classes, which can negatively affect model performance. This research aims to analyze the impact of oversampling techniques on the performance of the Long Short…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xv, 202 hlm.; ilus.; tab.; 29 cm.
- Series Title
- -
- Call Number
- T1929762026
PENDETEKSIAN SAMPAH BAWAH AIR MENGGUNAKAN METODE YOU ONLY LOOK ONCE DENGAN IN…
Plastic waste in aquatic ecosystems is a pressing global issue; however, underwater monitoring is often constrained by environmental conditions such as limited lighting and the small visual appearance of objects. Although the You Only Look Once (YOLO) algorithm excels in real-time detection, it still faces limitations in accurately detecting small objects. Therefore, this study aims to implemen…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xx, 143 hlm.; ilus.; tab.; 29 cm.
- Series Title
- -
- Call Number
- T1930022026
PENGEMBANGAN CHATBOT UNTUK KESEHATAN MENTAL DI ERA GENERASI Z MENGGUNAKAN FRA…
Generation Z is the largest demographic group in Indonesia and is increasingly vulnerable to mental health challenges. This study develops and evaluates a mental health chatbot using the Rasa framework and Natural Language Processing (NLP) to provide initial support for Generation Z. The chatbot was developed following the Rational Unified Process (RUP) methodology and integrated with the Teleg…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xvi, 84 hlm.; ilus.; tab.; 29 cm.
- Series Title
- -
- Call Number
- T1906862025
PENGENALAN PRODUK E-COMMERCE BERBASIS GAMBAR SECARA OTOMATIS MENGGUNAKAN CONV…
E-commerce has become a key pillar of the digital economy, supported by broad internet access and modern technology. However, text-based searches often cause difficulties, especially for products with complex descriptions. This study develops an automatic image-based e-commerce product recognition system using Convolutional Neural Network (CNN) with the VGG16 architecture. The Fashion Product I…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- x, 111 hlm.; ilus.; 29 cm
- Series Title
- -
- Call Number
- T1919602026
REKOGNISI WAJAH PADA CITRA BERESOLUSI RENDAH MENGGUNAKAN ARCFACE DENGAN RESTO…
This study addresses the challenge of face recognition in low-resolution images captured by Unmanned Aerial Vehicles (UAVs). We propose an integrated pipeline that utilizes Generative Facial Prior-Generative Adversarial Network (GFPGAN) for image restoration and ArcFace as a feature extractor. The system was evaluated on the DroneFace dataset across varying distances and heights, comparing Cosi…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xvii, 131 hlm.; ilus.; tab.; 29 cm.
- Series Title
- -
- Call Number
- T1923372026
PENERAPAN INDOBERT EMBEDDING DAN ALGORITMA SUPPORT VECTOR MACHINE (SVM) UNTUK…
Hate speech on social media is a serious issue that can trigger discrimination and social conflict, highlighting the need for an automated classification system to identify different types of hate speech. This study aims to develop an Indonesian hate speech classification system by combining IndoBERT embeddings as text representations and Support Vector Machine (SVM) as the classification algor…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xvi, 138 hlm.; ilus.; tab.; 29 cm.
- Series Title
- -
- Call Number
- T1923222026
ANALISIS KLASIFIKASI TINGKAT KEMISKINAN DENGAN ALGORITMA XGBOOST: STUDI KASUS…
Poverty remains a critical issue in Banyuasin Regency, South Sumatra, with a poverty rate of 9.31% in 2024, exceeding the national average of 8.47%. This study develops a poverty classification model using the XGBoost algorithm with SUSENAS 2024 data from Banyuasin Regency. The research employs 16 socioeconomic variables as features, with poverty status determined based on the Banyuasin poverty…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xvi, 155 hlm.; ilus.; tab.; 29 cm.
- Series Title
- -
- Call Number
- T1923102026
PENGEMBANGAN MEDIA PEMBELAJARAN MATEMATIKA BERBASIS PLATFORM GAME DIGITAL (RO…
This research is driven by the global perception of mathematics as a challenging subject that frequently induces anxiety among students, particularly at the secondary level. Digital Game-Based Learning (DGBL) has emerged as a proven strategy to significantly enhance student motivation and engagement. Digital platforms such as Roblox offer technological flexibility, allowing educators and studen…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xxii, VI-1 hlm.; ilus.; 29 cm
- Series Title
- -
- Call Number
- T1911902025
ANALISIS SEBARAN TOPIK ARTIKEL ILMIAH MENGGUNAKAN INDOBERT DAN K-MEANS
The significant increase in the number of scientific articles published along with advances in science and technology poses challenges in managing and organizing articles to support the efficiency of literature analysis. This research aims to develop a scientific article topic distribution analysis system by utilizing the IndoBERT model and the K-Means algorithm. The dataset used comes from 12 …
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xviii, 75 hlm.; ilus.; 29 cm
- Series Title
- -
- Call Number
- T1629752024
PENERAPAN METODE LONG-SHORT TERM MEMORY DAN FASTTEXT PADA KLASIFIKASI UJARAN …
Hate speech on digital platforms poses a serious threat to social cohesion as it can lead to discrimination, conflict, and violence. This highlights the importance of developing automated detection systems to mitigate its impact and create safer digital spaces. To address this challenge, this study aims to develop a hate speech classification model in the Indonesian language using the Long Shor…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- x, 83 hlm,; ilus.; 29 cm
- Series Title
- -
- Call Number
- T1629192024
KLASIFIKASI CITRA AKSARA HIRAGANA KUZUSHIJI MENGGUNAKAN SUPPORT VECTOR MACHIN…
Kuzushiji is a cursive writing style used in various classical Japanese manuscripts. Over time, this script has become difficult for modern readers to interpret. This condition encourages the need for research on the automatic classification of characters written in this style to support the study and understanding of classical Japanese texts. This study applies the Support Vector Machine (SVM)…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xv, 126 hlm.; ilus.; tab.; 29 cm.
- Series Title
- -
- Call Number
- T1903442025
IMAGE CAPTIONING UNTUK GENERASI PRA-DIAGNOSIS RADIOLOGI MENGGUNAKAN ARSITEKTU…
General vision-language models often face domain shift issues when applied to medical imaging. This study compares the performance of a general model (BLIP) against a medically pre-trained model (MedBLIP) for Chest X-ray reporting using the IU X-Ray dataset. Through quantitative metrics and expert pulmonologist validation, MedBLIP consistently outperformed BLIP, achieving a BLEU-4 of 0.0789, RO…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xv, 122 hlm.; ilus.; tab.; 29 cm
- Series Title
- -
- Call Number
- T1900742025
IMPUTASI DATA MEDIS HATI KRONIS MENGGUNAKAN ALGORITMA K- NEAREST NEIGHBORS IM…
Medical data related to chronic liver disease often contain missing values that can reduce the quality of data analysis and the accuracy of predictive models. Handling missing values properly is essential to ensure optimal classification performance. This study aims to apply and evaluate the K-Nearest Neighbor (KNN) Imputation method to address missing values in a medical dataset of liver cirrh…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xiii, 101 hlm.; ilus.; tab.; 29 cm
- Series Title
- -
- Call Number
- T1901092025
ANALISIS SENTIMEN PENGGUNA MEDIA SOSIAL X MENGENAI PINJAMAN ONLINE DENGAN PER…
The rapid development of technology and social media has transformed the way people express their opinions on various issues, including online loan services. Application X has become a primary platform for users to openly share their views. This study aims to analyze user sentiment toward online loan services by comparing the performance of the XGBoost and Random Forest algorithms. From an init…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xiii, 87 hlm.; ilus.; tab.; 29 cm
- Series Title
- -
- Call Number
- T1901022025
KLASIFIKASI TULISAN TANGAN ARAB DENGAN HYBRID MOMENT INVARIANT-BACKPROPAGATIO…
This study presents a comparative analysis of Arabic handwritten character classification using the Hybrid Moment Invariant–Backpropagation (HMI-BP) and Convolutional Neural Network (CNN) approaches. The morphological complexity of Arabic script and the high variability in writing styles among writers demand models capable of distinguishing visually similar characters. The Arabic Handwritten …
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xv, 139 hlm.; ilus.; tab.; 29 cm
- Series Title
- -
- Call Number
- T1899432025
KLASIFIKASI DIABETIK RETINOPATI DIABETES MELITUS MELALUI CITRA FUNDUS RETINA …
Diabetic retinopathy (DR) is a major complication of diabetes mellitus, characterized by damage to the retinal blood vessels and a high risk of blindness, particularly among individuals of productive age. Early detection of DR is essential, as the disease often presents no noticeable symptoms in its initial stages but can progress to permanent vision impairment if left untreated. This study aim…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xvii, 158 hlm.; ilus.; tab.; 29 cm
- Series Title
- -
- Call Number
- T1900622025
IMPLEMENTASI ADD-ON BLENDER UNTUK OTOMATISASI PEWARNAAN ACAK PADA OBJEK
3D object coloring is an important stage in digital design and animation, but this process often takes a long time and tends to be monotonous. This research aims to develop a Blender add-on called AutoColorize, designed using Python to automate the coloring process. The add-on is equipped with features to generate color palettes and apply colors to selected objects. The test results show that u…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xiv, 67 hlm.; ilus.; 29 cm
- Series Title
- -
- Call Number
- T1632352024
OPTIMASI FUZZY INFERENCE SYSTEMMODELMAMDANI DENGAN MENGGUNAKAN ALGORITMAPARTI…
Air is one of most importants thing in the world for all people, animals and plants. That’s why to check and maintain the air quality is one option to maintenance the world’s life. There are many way to check and maintain or even to predict the air polutions, and in this case i will use Fuzzy Inference System Mamdani. Not only with Fuzzy Inference System Mamdani, I will also optimize that w…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xvii, 67 hlm.; ilus.; 29 cm
- Series Title
- -
- Call Number
- T1631632024
FINE-TUNING MODEL ROBERTA UNTUK SISTEM TANYA JAWAB BERBASIS KONTEKS
The increasing amount of text-based information on the internet often requires users to read many long documents to find the answer information they need. Question Answering (QA) systems provide a solution to this problem by developing QA systems that can deliver direct answers from text without users having to read entire documents. This research focuses on developing an extractive question an…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xv, 101 hlm.; ilus.; tab.; 29 cm
- Series Title
- -
- Call Number
- T1898142025
KLASIFIKASI PENYAKIT ASMA DENGAN MENGGUNAKAN SELEKSI FITUR ANOVA F-TEST DAN A…
This study discusses the classification of asthma disease using Machine Learning algorithms to address three research questions: the application of Machine Learning in asthma classification, the effect of different dataset conditions, and the algorithm that produces the best performance. The asthma dataset obtained from Kaggle was processed under three scenarios: original, undersampling, and Sy…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xvii, 123 hlm.; ilus.; tab.; 29 cm.
- Series Title
- -
- Call Number
- T1899882025
PERBANDINGAN PERFORMA U-NET DAN SWIN UNETR PADA SEGMENTASI CITRA MRI TUMOR OTAK
Brain tumors require rapid and accurate diagnosis, while manual segmentation of Magnetic Resonance Imaging (MRI) scans is time-consuming and highly dependent on expert knowledge. This study compares the performance of two deep learning architectures for brain tumor segmentation, namely 3D U-Net and Swin UNETR, trained and validated using the BraTS dataset and evaluated on unseen cases. Model pe…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xvi, 138 hlm.; ilus.; tab.; 29 cm
- Series Title
- -
- Call Number
- T1900062025
PENGEMBANGAN DIALOG ADAPTIF MENGGUNAKAN KECERDASAN BUATAN GENERATIF PADA GIM …
The use of generative artificial intelligence (AI) technology has brought breakthroughs in game development, particularly in the visual novel genre. This research aims to develop adaptive dialogue systems based on generative AI, which can enhance player experience by creating more dynamic and personalized interactions. The system is designed to produce more varied dialogues by leveraging genera…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xvi, 90 hlm.; ilus.; tab.; 29 cm
- Series Title
- -
- Call Number
- T1900092025
ANALISIS SENTIMEN KOMENTAR PENGGUNA TERHADAP LAYANAN PAYLATER DI PLATFORM X M…
The rapid growth of digital financial services in Indonesia has accelerated the adoption of PayLater features across various online transaction platforms. This trend has led to diverse public opinions and sentiments, particularly on social media platform X (Twitter). This study aims to analyze public sentiment toward PayLater services and compare the performance of the Bidirectional Long Short-…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xiv, 97 hlm.; ilus.; tab.; 29 cm.
- Series Title
- -
- Call Number
- T1900552025
DETEKSI HUMOR TEKS PENDEK MENGGUNAKAN MODEL INDOBERT
The rapid growth of Indonesian text content on social media has increased the need for automatic systems capable of accurately detecting humor, as humor often contains implicit meanings, wordplay, and cultural context. This study develops an Indonesian short-text humor detection system using a fine-tuning approach on the IndoBERT model. The objective of this research is to classify text into tw…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xv, 158 hlm.; ilus.; tab.; 29 cm.
- Series Title
- -
- Call Number
- T1900562025
REKOMENDASI PEMILIHAN SEKOLAH MENENGAH PERTAMA BERBASIS ISLAM KOTA PALEMBANG …
Islamic education plays an important role in shaping students’ character and intelligence through the integration of knowledge and Islamic values. In Palembang City, the increasing public interest in Islamic-based junior high schools (SMP) has created challenges for parents in selecting the most appropriate school due to limited information and the complexity of decision criteria, such as sch…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xv, 124 hlm.; ilus.; tab.; 29 cm.
- Series Title
- -
- Call Number
- T1898152025
PENGEMBANGAN GAME MULTIPLAYER GUNTING BATU KERTAS BERBASIS DETEKSI GERAKAN TA…
In the era of computer vision and machine learning advancement, the integration of gesture recognition technology in interactive gaming continues to evolve. This study aims to develop a multiplayer rock-paper-scissors game based on hand gesture detection using MediaPipe and real-time communication with Socket.IO. The MediaPipe Hands model is utilized to detect and classify hand gestures, while …
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xv, 98 hlm.; ilus.; tab.; 29 cm.
- Series Title
- -
- Call Number
- T1897352025
KLASIFIKASI EMOSI PADA LIRIK LAGU BERBAHASA INDONESIA DENGAN FINE-TUNING INDO…
The rapid growth of digital music platforms and the increasing availability of Indonesian song lyrics have created a demand for automatic emotion identification to support content analysis and mood-based recommendation. However, emotion classification in song lyrics is challenging due to subjective interpretation, figurative language, and class imbalance across emotion categories. This study ai…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xiv, 126 hlm.; ilus.; tab.; 29 cm
- Series Title
- -
- Call Number
- T1899322025
OPTIMALISASI DETEKSI WAJAH KECIL BERBASIS YOLOV11 MENGGUNAKAN SAHI DAN REAL-E…
This study addresses the critical challenge of micro-scale face detection in lowresolution surveillance imagery by proposing a hybrid pipeline integrating YOLOv11-pose, Slicing Aided Hyper Inference (SAHI), and Real-ESRGAN using a two-phase methodology on the WIDER FACE dataset enriched with 5-point landmark annotations. The first phase focuses on architectural optimization, where YOLOv11s-pose…
- Edition
- -
- ISBN/ISSN
- -
- Collation
- xv, 136 hlm.; ilus.; tab.; 29 cm
- Series Title
- -
- Call Number
- T1899522025
Computer Science, Information & General Works 
Philosophy & Psychology 
Religion 
Social Sciences 
Language 
Pure Science 
Applied Sciences 
Art & Recreation 
Literature 
History & Geography