39 research outputs found
Comparison of Machine Learning Methods (Linear Regression, Random Forest, and XGBoost) for Predicting Poverty in Central Java in 2024
No full textPoverty is a major issue faced by Central Java Province, with rates fluctuating annually. To respond to and address this challenge more effectively, a predictive, data-driven approach is essential. This study applies machine learning techniques to forecast the number of people living in poverty in 2024 at the district/city level, utilizing socio-economic data from 2019 to 2023 provided by the Central Bureau of Statistics (BPS). Seven indicators are used as predictor variables, including the poverty line, the number and percentage of people living in poverty, the open unemployment rate, average years of schooling, the Human Development Index, and the regional minimum wage. The data were normalized using StandardScaler and split into training (80%) and testing (20%) sets. This study compares three regression algorithms—Linear Regression, Random Forest, and XGBoost—to evaluate their effectiveness in modeling the complexity of socio-economic data. The analysis reveals that XGBoost delivers the best performance, with a Mean Absolute Error (MAE) of 6,665 and an R² score of 0.978, outperforming Random Forest (MAE: 9,209; R²: 0.947) and Linear Regression (MAE: 10,917; R²: 0.896). By comparing these models, the study addresses a gap in the literature regarding the effectiveness of machine learning models for local-level poverty prediction. The findings suggest that XGBoost holds strong potential as a data-driven policy support tool, particularly in poverty alleviation planning and decision-making at the regional level
Algoritma matching bobot maskimum dalam graph bipartit komplit berboto
No full textABSTRAK
Suatu matching dalam graph G adalah subgraph 1-regular pada G yang disebabkan oleh kumpulan dart pasangan garis yang tidak adjacent. Suatu matching merupakan matching maksimum bila matching tersebut mempunyai harga pokok maksimum. Matching dalam graph bipartit merupakan matching maksimum apabila tidak adanya path perluasart yang berkenaan dengan matching tersebut.
Matching yang mempunyai bobot maksimum disebut matching bobot maksimum. Matching bobot maksimum dalam graph bipartit komplit berbobot diperoleh dengan mencari matching maksimum dalam subgraph pada graph bipartit komplit berbobot, kemudian dibangun sampai didapatkan matching perfek atau setiap titik dalam V merupakan titik matched.
A matching in a graph G is a 1-regular subgraph of G, that is, a subgraph induced _by a collection of pairwise nonadjacent edges. A matching is called maximum matching if the matching have maximum cardinality. A matching in a bipartite graphs is a maximum matching if there exists no augmenting path.
A matching in which the sum of the weights of maximum its edges is called maximum weight matching. A maximum weight matching in weighted complete bipartite graphs is got to find maximum matching in subgraph to weighted complete bipartite graphs, further its construct to arrived is got perfec matching or each vertex in V is matched vertex
Evaluasi Performa YOLOv12 untuk Deteksi Plat Nomor Kendaraan Real-Time pada Citra Closed-Circuit Television (CCTV)
No full textLicense plate detection is a crucial component of intelligent transportation systems. Deep learning methods still face limitations in detecting small-sized plates under low-light conditions and complex backgrounds. This study evaluates YOLOv12's performance for license plate detection in CCTV imagery containing small objects with great visual detail. Unlike YOLOv11, which focuses on detection efficiency for larger objects, YOLOv12 integrates attention mechanisms to enhance sensitivity to fine-grained spatial features. Model evaluation was conducted using precision, recall, and mean average precision (mAP) metrics on traffic image datasets with daytime and nighttime lighting conditions and CCTV viewing angles. Results show the model achieves [email protected] of 87.2% and precision of 89.5%, comparable to previous YOLO-based studies. However, performance drops to 47.9% at [email protected]:0.95, indicating limitations in bounding-box localization precision under visually complex conditions. This study highlights opportunities for future improvement through dataset expansion and parameter optimization for training
Pengembangan Sistem Informasi Dengan Metode Waterfall Untuk Pengarsipan Data Wajib Pajak
No full textKantor pelayanan pajak (KPP) merupakan Kantor yang berfungsi melayani wajib pajak dalam aktivitas pembayaran pajak. Kantor Pelayanan Pajak sejatinya mempunyai data-data yang terkait dengan wajib pajak. KPP Pratama Kudus merupakan salah satu Kantor pelayanan pajak yang terdapat di Jawa Tengah. Dalam aktifitasnya, penggunaan metode konvensional dalam pengelolaan data arsip menyebabkan kendala dalam pencarian data wajib pajak. Dalam paper ini telah dibangun sebuah sistem informasi pengarsipan data wajib pajak yang mempunyai fitur pendaftaran, login, dan pengelolaan data wajib pajak. Analisis dan perancangan menggunakan metode berorientasi objek yakni menggunakan diagram-diagram UML seperti use case diagram dan activity diagram. Implementasi dilakukan dengan menggunakan tool netbean untuk Bahasa pemrograman java dan MySQL sebagai database. Berdasarkan hasil implementasi dan pengujian yang dilakukan menggunakan metode black box didapatkan bahwa sistem informasi pengarsipan yang dibangun dapat membantu dan meningkatkan kinerja di Kantor pelayanan pajak pratama kudus.</p
Lung Cancer Classification using the Naïve Bayes Method with SMOTE
No full textThe primary challenges addressed in this study include delays in the early detection of lung cancer due to non-specific initial symptoms, the limitations of the Naïve Bayes algorithm in processing categorical data such as symptoms, gender, and smoking habits, as well as class imbalance issues in the dataset that can affect model accuracy. To overcome these challenges, the SMOTE (Synthetic Minority Over-sampling Technique) method was applied to improve classification performance. This study aims to implement the Naïve Bayes algorithm for lung cancer classification and compare its performance on imbalanced data versus data balanced using SMOTE. The methodology consists of data preprocessing, encoding, applying SMOTE for balancing, and classification using Naïve Bayes. Evaluation was performed using three data split ratios: 80:20, 70:30, and 60:40. The results show that applying SMOTE led to performance improvements, with the most significant gains observed at the 60:40 split ratio. In this case, model accuracy improved from 88.29% to 93.19%. For the “Yes” (positive) class, precision remained at 0.96, recall at 0.91, and F1-score at 0.93. However, for the “No” (negative) class, precision improved from 0.40 to 0.90, recall from 0.60 to 0.96, and F1-score from 0.48 to 0.93. Conversely, slight decreases in accuracy were observed for the 80:20 and 70:30 ratios after SMOTE application. These findings demonstrate that SMOTE significantly enhances model performance at the 60:40 ratio, not only in terms of accuracy but also in recall and F1-score, which are crucial for reducing false negatives in the minority (“Yes”) class. This is especially critical in early detection, as correctly identifying actual cancer cases is more important than merely maintaining overall accuracy. Although SMOTE did not always improve accuracy at other ratios, it still contributed to better cancer case detection. Therefore, its application should be considered carefully, balancing overall accuracy with clinically meaningful metrics
PEMANFAATAN EDUCATIONAL DATA MINING (EDM) UNTUK MEMPREDIKSI MASA STUDI MAHASISWA MENGGUNAKAN ALGORITMA C4.5 (STUDI KASUS: TI-S1 UDINUS)
No full textTersedianya data yang melimpah pada institusi pendidikan harus dimanfaatkan dengan baik. Menemukan pola studi mahasiswa dan hubungan antar atribut-atribut data pendidikan yang mempengaruhi masa studi mahasiswa dalam suatu data besar, menjadi kajian dalam penelitian ini. Data mining dapat diusulkan sebagai salah satu pendekatan yang dapat dilakukan untuk memprediksi kinerja siswa. Algoritma C4.5 diterapkan untuk menemukan pola klasifikasi terhadap mahasiswa yang telah lulus tepat waktu dan tidak tepat waktu serta melakukan prediksi terhadap data uji yang diberikan. Hasil akurasi menunjukkan algoritma C4.5 mampu melakukan prediksi dengan baik (73,68%) terhadap masa studi mahasiswa yang tepat waktu dan tidak tepat waktu. Penerapan Data Mining pada bidang pendidikan (Educational Data Mining) memberikan kemajuan dan kontribusi besar pada dunia pendidikan dan pada bidang riset data mining. Â Kata kunci: Data Mining, EDM, Masa Studi Mahasiswa, Algoritma C4.5, Decision Tre
Tingkat Kesulitan Adaptif pada Android Game bertema Flora Fauna Endemik Indonesia dengan Fuzzy Logic
No full textAbstract. Adaptive Difficulty Level on Android of Indonesian Endemic Plants and Animals with Fuzzy Logic. The education of protecting endemic plants and animals in Indonesia requires the raising public awareness. One attempt is to develop an interactive digital games application. However, not all games are interesting to play. High boredom and frustration zones are also caused by the game content and level repetition that are not suitable for children's playing level. In this study, an Android-based educational game with theme Indonesian endemic plants and animals has been created with an adaptive level of difficulty according to the player's ability. The game mechanism is card gameslike with artificial intelligence using Sugeno Fuzzy logic which can automatically estimate the game level by drawing the card type at the game according to the player's ability. The results show that Sugeno Fuzzy made 35 correct decisions and 15 false decisions from 50 trials.
Keywords: animals and plants, game, adaptive difficulty, fuzzy, testing
Abstrak. Edukasi untuk melindungi flora dan fauna endemik di Indonesia diperlukan untuk menumbuhkan kesadaran bagi masyarakat. Salah satunya dengan aplikasi dari game digital yang interaktif. Namun, tidak semua game menarik untuk dimainkan. Zona bosan dan zona frustasi yang tinggi juga disebabkan karena pengulangan kasus dan tingkat permainan yang kurang sesuai dengan kemampuan bermain anak-anak. Pada penelitian ini diciptakan suatu game edukasi berbasis Android bertema flora dan fauna endemik Indonesia dengan tingkat kesulitan yang adaptif sesuai kemampuan pemain. Mekanisme game yang dibuat seperti game kartu dengan kecerdasan buatan menggunakan logika Fuzzy Sugeno yang mampu mempertimbangkan langsung tingkat permainan dengan cara mengeluarkan jenis kartu dalam lapangan permainan yang sesuai dengan kemampuan pemain. Hasil pengujian memperlihatkan Fuzzy Sugeno dapat membuat 35 keputusan dan 15 nilai pasti dari 50 kali percobaan.
Kata Kunci: flora dan fauna, game, tingkat kesulitan adaptif, fuzzy, pengujia
Prediksi Penjualan Tanaman Hias menggunakan Regresi Linier Berganda dengan Perbandingan Eliminasi Gauss dan Cramer
No full textSales prediction is a crucial element in the ornamental plant business to support inventory planning and marketing strategies. Our research aims to compare the Gauss and Cramer elimination methods (determinant matrix) in multiple linear regression to assess the accuracy of sales prediction. Gauss elimination is effective for systems of large size, while the Cramer method is more consistent in handling systems of linear equations that have correlated variables. The dataset used consists of 212 data points, including unit price as the dependent variable and stock, quantity sold, and total revenue as the independent variables. The accuracy was compared using Mean Absolute Percentage Error (MAPE) due to its ability to measure the error relative to the true value. Our findings show that the Cramer method has a MAPE of 21%, which is lower than Gauss elimination with a MAPE of 40%, making it more accurate in sales prediction. With a more precise method, business owners can optimize inventory management, set prices more efficiently, and devise data-driven marketing strategies. Our results also provide insights for other sectors that use predictive analytics to improve business decision-making
