Master Theses
Master Theses
Recently added
Now showing items 1-20 of 620
-
Analisis Kinerja Model Support Vector Machine (Svm) Melalui Optimasi Parameter dengan Genetic Algorithm (Ga) pada Klasifikasi Penyakit Ginjal Kronis
(Universitas Sumatera Utara, 2025)This study uses hyperparameter optimization to improve accuracy in classifying chronic kidney disease (CKD) through the Support Vector Machine (SVM) algorithm. SVM is combined with the Grid Search technique for hyperparameter ... -
Optimasi Model Credit Scoring dengan Random Forest dan XGBoost
(Universitas Sumatera Utara, 2025)This study highlights the importance of addressing class imbalance in credit score model datasets to achieve accurate risk prediction, especially in identifying rare default cases The SMOTETomek technique is proven to be ... -
Analisis Kinerja Kombinasi Algoritma Genetika Dan Logika Fuzzy Dalam Optimasi Penjadwalan Pelayanan Kapal Di Pelabuhan Belawan
(Universitas Sumatera Utara, 2025)Vessel service scheduling is one of the key challenges in efficient port logistics management, which requires careful handling of variables such as capacity, time, and priority. In an effort to optimize this process, this ... -
Optimisasi Metode Klasifikasi KNN, SVM, dan SVM Kernel pada Prediksi Potabilitas Air dengan Pendekatan Hyperparameter
(Universitas Sumatera Utara, 2025)his research focuses on optimizing the K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and SVM Kernel classification methods using a hyperparameter approach to improve the accuracy of water potability prediction. ... -
Hybrid Cryptosystem dengan Algoritma Cramer-Shoup dan Spritz untuk Pengamanan Dokumen Digital
(Universitas Sumatera Utara, 2024)Symmetric algorithms are known for their speed but face significant challenges in secure key distribution, as the same key must be shared between sender and receiver, which makes it vulnerable to interception. In contrast, ... -
Peningkatan Akurasi Prediksi pada Jaringan IoT terhadap Serangan DDOS dengan Kombinasi Algoritma Ripper dan Algoritma KNN
(Universitas Sumatera Utara, 2024)The Internet of Things (IoT) encompasses a network of interconnected devices that communicate through the internet, integrating sensors, software, and other technologies. As the number of connected devices grows, ensuring ... -
Pengembangan Algoritma Genetika dan Self Organizing Maps (SOM) untuk Prediksi Saham pada Emiten yang Terdaftar di PT. Bursa Efek Indonesia
(Universitas Sumatera Utara, 2024)The development of methods or tools to determine stock price movements is currently being developed to minimize risks for stock traders and investors in making investment decisions on issuers listed on the Indonesian ... -
Analisis Kinerja Word Embedding Glove dalam Penerjemahan Bahasa Batak-Inggris
(Universitas Sumatera Utara, 2024)This study examines the performance of GloVe word embedding on the Long Short-Term Memory (LSTM) model in translating from Batak to English. GloVe has the ability to capture semantic meaning from a wide context of words. ... -
Algoritma Hibrid Menggunakan CNN dan LSTM untuk Peningkatan Performansi pada Klasifikasi Citra Lesi Kulit
(Universitas Sumatera Utara, 2024)Skin lesions areacondition of abnormal growths or changes in theappearanceofthe skin, such as lumps, abrasions, cysts, or colordifferences. Skin lesionscan bedetected as cancerous and non-cancerous. Detecting earlier skin ... -
Kombinasi Metode 2DPCA (Two-Dimensional Principal Component Analysis), sPCA (sparse Principal Component Analysis), dan Ridge Regression Model dalam Pengenalan Wajah
(Universitas Sumatera Utara, 2024)The 2DPCA (Two-Dimensional Principal Component Analysis) method, an extension of the PCA (Principal Component Analysis) method, is commonly used in pattern recognition to represent complex data in lower dimensions. One ... -
Pengembangan Model Deep Learning Menggunakan Fine-Tuning ResNet-18 untuk Diagnosis Leukemia Akut pada Blood Smear Images
(Universitas Sumatera Utara, 2024)This study presents an investigation of fine-tuning ResNet-18 model for the precise diagnosis of acute leukemia from blood smear images. Early detection of acute leukemia is crucial for improving patient prognosis. Despite ... -
Menentukan Parameter K pada K-Nearest Neighbors (KNN) Menggunakan Random Grid Search
(Universitas Sumatera Utara, 2024)This research aims to optimise the classification of trainee acceptance using the K-Nearest Neighbors (KNN) algorithm by finding the optimal value for the K parameter through a combination of Random Search and Grid ... -
Optimasi Kombinasi Parameter Cost dan Kernel SVM melalui Gridsearch
(Universitas Sumatera Utara, 2024)The aim of this research is to improve the performance of the Support Vector Machine (SVM) algorithm in determining the values of Cost and Kernel parameters using the GridSearch technique. This study focuses on sentiment ... -
Cryptography Random Algorythm (CRA) untuk Mengantisipasi Serangan dengan Brute Force
(Universitas Sumatera Utara, 2024)One type of algorithm that is often used to secure data is the asymmetric algorithm, where this algorithm is widely used by business entities and governments to secure data. We know that this algorithm relies on two keys ... -
Peningkatan Akurasi Support Vector Machine pada Klasifikasi Pengaduan Masyarakat Menggunakan Algoritma Firefly
(Universitas Sumatera Utara, 2024)Public complaint services need to receive responses promptly from the relevant department. Therefore, a text classification system with best accuracy is needed. One of the methods used is the Support Vector Machine (SVM). ... -
Unjuk Kerja Term Frequency – Inverse Document Frequency dan K-Means dalam Identifikasi Layanan Pemerintah
(Universitas Sumatera Utara, 2024)Term Frequency-Inverse Document Frequency (TF-IDF) is used to assess the importance of words in a document relative to the rest of the document set, while K-Means clusters documents based on content similarity. Utilizing ... -
Teknik Peningkatan Performa Algoritma RSA dalam Pengamanan Data Dokumen
(Universitas Sumatera Utara, 2024)Advances in information system technology have allowed for the extensive exchange of data between users without spatial and temporal restrictions, but they also carry security risks related to information confidentiality. ... -
Klasifikasi Sentimen Menggunakan Algoritma K-NN Berdasarkan Pendekatan Random Search Cross Validation
(Universitas Sumatera Utara, 2024)This research discusses sentiment classification using the K-Nearest Neighbor (K-NN) algorithm with the RANDOM SEARCH CROSS VALIDATION (RSCV) approach. This method aims to classify ChatGPT app user reviews into three ... -
Pengenalan Area Berbasiskan Struktur GRID: Studi Kasus pada Tanaman Padi Sawah dengan Wireless Sensor Network
(Universitas Sumatera Utara, 2024)In the modern era of agriculture, efficient and effective monitoring of agricultural land, particularly the meadow, is critical to enhancing production and crop quality. The objective of the research is to create a grid-based ... -
Pemilahan Limbah Padat Berbahaya dan Beracun (B3) Menggunakan Teknik Pembelajaran Ensemble dengan Arsitektur VGG-16 dan Densenet – 121
(Universitas Sumatera Utara, 2024)Waste has become one of the increasingly concerning environmental issues, escalating alongside population growth and human activities. According to data obtained from the Integrated Environmental and Forestry Information ...
RSS 1.0