Claim Missing Document
Check
Articles

Found 15 Documents
Search

The Application of Modeling Gamma-Pareto Distributed Data Using GLM Gamma in Estimation of Monthly Rainfall with TRMM Data Herlina Hanum; Aji Hamim Wigena; Anik Djuraidah; I Wayan Mangku
Sriwijaya Journal of Environment Vol 2, No 2 (2017): Water As A Vital Resource for Life
Publisher : Program Pascasarjana Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (911.747 KB) | DOI: 10.22135/sje.2017.2.2.40-45

Abstract

As a recently developed distribution, the application of Gamma-Pareto is limited to single variable modeling.  A specific transformation of Gamma-Pareto (G-P) yields gamma distribution. Therefore, it is possible to use analysis based on gamma distribution (e.g. GLM) for modeling G-P distributed data.  In this paper we study the application of modeling G-P distributed data using GLM gamma for monthly rainfall which observed in Sukadana Station.  The modeling aims to analyze whether Tropical Rainfall Measuring Mission (TRMM) satellite data is a good estimator for unobserved station’s data.  The transformed of station’s data were considered as response variable in GLM gamma.  The explanatory variable is TRMM data in 9 grids around the station. There are two kinds of modeling i.e. model for whole data and extreme data. The results show that for both data the station’s data are G-P distributed and the transformed data are gamma distributed.  TRMM rainfall data at each grid around the station can be used to estimate the observed data of monthly rainfall. The best model for both data contains dummy variables which correspond to inter quantile data.  The coefficients of dummy variables in the best model may substitute the grouping or the correction in the previous studies.
Efektivitas Peraturan Pemerintah Republik Indonesia Nomor 2 Tahun 2003 dalam Penegakan Kode Etik Profesi Polri di Satuan Brimob Polda Sumatera Utara Universitas Muslim Nusantara Al Washliyah, Echo Agung Wichaksono; Herlina Hanum
Albayan Journal of Islam and Muslim Societies Vol. 1 No. 01 (2024)
Publisher : Albayan Journal of Islam and Muslim Societies

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study aims to analyze the effectiveness of the implementation of Government Regulation of the Republic of Indonesia Number 2 of 2003 on the Disciplinary Regulations of Police Officers in the enforcement of the Indonesian National Police Professional Code of Ethics (KEPP) within the Brimob Unit of the North Sumatra Regional Police. Employing a qualitative approach with normative-empirical design, data were collected through interviews, observations, and document analysis. The findings demonstrate the regulation’s effective enforcement, indicated by a yearly decrease in disciplinary violations. Nonetheless, implementation is challenged by the limited number of accredited personnel and the procedural requirement that disciplinary hearings be conducted at the provincial police headquarters. These findings highlight the necessity for capacity-building and structural reforms within the police institution to ensure just and efficient discipline enforcement
Analisis Perbandingan Prediksi Harapan Hidup Hepatitis Menggunakan Algoritma K-Nearest Neighbor dan C4.5 Karina; Herlina Hanum; Anita Desiani
Jurnal Ilmiah Informatika Vol. 8 No. 2 (2023): Jurnal Ilmiah Informatika
Publisher : Department of Science and Technology Ibrahimy University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35316/jimi.v8i2.98-111

Abstract

Hepatitis is an inflammatory disease of the liver caused by a virus that causes damage to the cells and function of the liver. This study compares the accuracy, precision, and recall results of the K-Nearest Neighbor (K-NN) and C4.5 algorithms using the Percentage Split and K-fold Cross Validation methods. Of the two algorithms, the best level of accuracy is obtained using the K-fold Cross Validation method. Based on the accuracy and error rate, the best algorithm for predicting life expectancy for hepatitis sufferers is the K-NN algorithm. Based on the special Precision and Recall values ​​on the Recall value to predict class zero the best algorithm is obtained using the C4.5 algorithm. To assess Precision and Recall, the other best algorithm in predicting the fixed response variable is obtained by using the K-NN algorithm. Overall, the best algorithm for predicting life expectancy for hepatitis sufferers is the K-Nearest Neighbor (K-NN) algorithm.
Peran Badan Pengawas Obat dan Makanan terhadap Sanksi Pidana dalam Peredaran Produk Kosmetik yang Tidak Memiliki Izin di Kota Medan Dormauli Manurung; Herlina Hanum
Birokrasi: JURNAL ILMU HUKUM DAN TATA NEGARA Vol. 4 No. 1 (2026): Maret: Birokrasi: JURNAL ILMU HUKUM DAN TATA NEGARA
Publisher : Sekolah Tinggi Ilmu Administrasi (STIA) Yappi Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/birokrasi.v4i1.2537

Abstract

The development of the cosmetics industry has had both positive and negative impacts on consumers, particularly in Medan City. The high demand for cosmetics has driven irresponsible business actors to produce and distribute cosmetics without distribution permits from the National Agency of Drug and Food Control (BPOM). This study aims to analyze the role of BPOM in supervising illegal cosmetics, examine criminal sanction enforcement, and identify obstacles faced by PPNS investigators at BBPOM Medan. A qualitative empirical juridical approach with field research method was used, employing in-depth interviews, observation, and documentation. The primary informant is the Head of BBPOM Medan. Results show BPOM supervises through pre-market and post-market control, enforcement, and public education. Criminal sanctions under Article 435 of Law No. 17 of 2023 impose up to 12 years imprisonment or Rp5 billion fine. Key obstacles include limited investigator legal expertise, budget constraints, low public participation, fleeing suspects, and files returned by prosecutors. Strengthening investigator capacity, improving inter-agency coordination, and increasing public awareness are urgently needed.
Perbandingan Algoritma CART Dan AdaBoost Pada Klasifikasi Demensia Muhammad Arya All Fajri; M Aldi Saputra; Anita Desiani; Bambang Suprihatin; Herlina Hanum
FORMAT Vol 15 No 1 (2026)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/format.2026.v15.i1.002

Abstract

Demensia merupakan gangguan kesehatan ditandai dengan penurunan daya ingat, kemampuan kognitif, dan perilaku yang mengganggu aktivitas pada kehidupan sehari-hari. Masyarakat kurang mendapatkan informasi mengenai deteksi dini demensia yang disebabkan terbatasnya fasilitas kesehatan. Klasifikasi menggunakan data mining dapat membantu deteksi dini demensia. Penelitian ini bertujuan membandingkan algoritma CART dan AdaBoost untuk melihat metode yang paling efektif digunakan pada klasifikasi demensia. Pembagian data dilakukan menggunakan metode percentage split dan k-fold cross-validation. Percentage split membagi data menjadi dua bagian dengan 70% data pelatihan dan 30% data pengujian. K-fold cross-validation mengelompokkan data dengan 1 kelompok data menjadi data pengujian dan 9 kelompok data lainnya menjadi data pengujian yang dilakukan berulang pada setiap kelompok data sebanyak 10 kali. ADASYN digunakan untuk menyeimbangkan data pada setiap kelas. Hasil evaluasi kinerja pada kedua algoritma menunjukkan AdaBoost menggunakan ADASYN dan k-fold cross-validation memiliki nilai tertinggi untuk akurasi, presisi, recall, f1-score, dan ROC-AUC masing-masing sebesar 92.52%, 92.11%, 92.52%, 91.46%, dan 96.85%. Hasil ini menunjukkan bahwa algoritma AdaBoost sangat baik dalam memprediksi seluruh demensia dengan benar, mempertahankan keseimbangan antara presisi dan recall, dan membedakan tiga kelas demensia. Hasil penelitian menunjukkan keunggulan pendekatan ensemble learning dalam menangani variasi data dan meningkatkan stabilitas model klasifikasi demensia. Penelitian ini menunjukkan bahwa AdaBoost memiliki performa yang sangat baik dibandingkan CART pada klasifikasi demensia.