Article Per Year (5 Year)
p-Index From 2021 - 2026
2.863
P-Index
This Author published in this journals
All Journal Jurnal Transformatika JITK (Jurnal Ilmu Pengetahuan dan Komputer) Jurnal Pengembangan Rekayasa dan Teknologi Variance : Journal of Statistics and Its Applications LOSARI: Jurnal Pengabdian Kepada Masyarakat Jurnal Abdi Masyarakat Indonesia Journal Of Human And Education (JAHE) Berita Kedokteran Masyarakat Journal of Data Insights Prosiding Seminar Nasional Unimus
Dannu Purwanto
Universitas Muhammadiyah Semarang
Agriculture, Biological Sciences & Forestry Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Mechanical Engineering Nursing Public Health Social Sciences Transportation Other

Published : 18 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 18 Documents
Search

 1   2 
DASHBOARD LINGKUNGAN HIDUP UNTUK ANALISIS DIARE MENGGUNAKAN METODE K-MEANS CLUSTERING Sitti Sahara; Saeful Amri; Ariska Fitriyana Ningrum; Dannu Purwanto
Journal of Data Insights Vol 2 No 1 (2024): Journal of Data Insights
Publisher : Department of Sains Data UNIMUS Universitas Muhammadiyah Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jodi.v2i1.210

Abstract

Abstrak Singkat: Diare adalah penyakit umum dengan penyebab yang beragam, termasuk virus, bakteri, dan faktor-faktor lainnya. Faktor-faktor lingkungan, gizi yang buruk, dan kurangnya pengetahuan masyarakat berperan penting dalam tingginya kasus diare, terutama pada anak-anak di bawah lima tahun, di Indonesia. Analisis cluster digunakan untuk mengelompokkan daerah berdasarkan kasus diare dan membantu perencanaan penanggulangan. Penelitian ini menggunakan data BPS 2021 dari 34 provinsi di Indonesia dan berfokus pada faktor penyebab diare. Penelitian ini bertujuan untuk memahami faktor-faktor yang berkontribusi pada kasus diare, dengan harapan dapat merumuskan strategi penanggulangan yang lebih efektif.
Application of Random Forest Method to Analyze the Effect of Smoking History on The Type and Outcomes of TB Examinations: Penerapan Metode Random Forest Untuk Menganalisis Pengaruh Riawayat Merokok Terhadap Tipe dan Hasil Pemeriksaan Pasien TBC Dannu Purwanto; Novia Yunanita
Journal of Data Insights Vol 2 No 2 (2024): Journal of Data Insights
Publisher : Department of Sains Data UNIMUS Universitas Muhammadiyah Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jodi.v2i2.651

Abstract

Tuberculosis (TB) continues to pose a major global health challenge, especially in developing countries. One of the key risk factors that exacerbates the condition of TB patients is smoking, which increases susceptibility to infections and worsens disease prognosis. This study aims to evaluate the influence of smoking history on the type and outcomes of TB diagnoses using a Random Forest machine learning model. The dataset comprises information from TB-diagnosed patients, including demographic details such as age, gender, smoking status, patient type, and diagnostic results. The Random Forest model achieved an accuracy of 87.36%, performing best in classifying non-TB-infected patients. However, the model struggled to accurately identify healthy individuals without TB, likely due to data imbalance. This research offers fresh insights into the potential of machine learning to enhance TB diagnosis and prevention, while deepening the understanding of smoking as a risk factor in TB management.
Comparison of Holt-Winters Exponential Smoothing (HWES) and Singular Spectrum Analysis (SSA) Methods in Forecasting the Number of Passengers at PT KAI in Indonesia: Perbandingan Metode Holt-Winters Exponential Smoothing (HWES) Dan Singular Spectrum Analysis (SSA) Pada Peramalan Jumlah Penumpang PT KAI di Indonesia Samikoh Ulinuha; Tiani Wahyu Utami; Prizka Rismawati Arum; Dannu Purwanto
Journal of Data Insights Vol 2 No 2 (2024): Journal of Data Insights
Publisher : Department of Sains Data UNIMUS Universitas Muhammadiyah Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jodi.v2i2.654

Abstract

Penelitian ini mengkaji penerapan dua metode peramalan, yaitu Holt Winters Exponential Smoothing (HWES) dan Singular Spectrum Analysis (SSA), dalam meramalkan jumlah penumpang di PT Kereta Api Indonesia. Hasil penelitian menunjukkan bahwa penerapan metode HWES dengan model additive menghasilkan nilai parameter pemulusan optimal dengan alpha , beta dan gamma model ini memiliki nilai MAPE sebesar 10.75%. Sementara itu, pada HWES model multiplicative menghasilkan nilai parameter pemulusan alpha , beta dan gamma , menghasilkan nilai MAPE 14.50%. Metode SSA dengan window length menghasilkan nilai MAPE 13.33%. Perbandingan nilai MAPE anatara metode HWES additive, HWES multiplicative dan SSA menunjukkan bahwa HWES additive lebih unggul dengan MAPE sebesar 10.75%. Peramalan jumlah penumpang Kereta Api Indonesia menggunakan metode terbaik Holt Winters Exponential Smoothing Additive untuk periode Januari hingga Desember 2024 memperlihatkan variasi jumlah penumpang terendah pada bulan Agustus dan tertinggi pada bulan Januari.
Evaluation of Deep Learning Optimizers for Predicting JISDOR Exchange Rates Using LSTM Networks: Evaluasi Pengoptimalan Deep Learning untuk Memprediksi Nilai Tukar JISDOR Menggunakan Jaringan LSTM Ariska Fitriyana Ningrum; Dannu Purwanto; Amelia Kusuma Wardani
Journal of Data Insights Vol 3 No 1 (2025): Journal of Data Insights
Publisher : Department of Sains Data UNIMUS Universitas Muhammadiyah Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jodi.v3i1.726

Abstract

This research explores the application of four optimization algorithms—Adam, Nadam, RMSProp, and SGD—on a Long Short-Term Memory (LSTM) model to forecast the Jakarta Interbank Spot Dollar Rate (JISDOR). The volatile nature of exchange rate data, influenced by global and domestic economic dynamics, necessitates the use of models like LSTM that excel in capturing both short- and long-term dependencies. Performance was assessed using metrics such as Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). Among the optimizers, Nadam proved to be the most effective, achieving the lowest RMSE of 62.767 and a MAPE of 0.003, indicating its capability in managing complex fluctuations in the dataset. Despite Nadam's promising results, opportunities for improvement remain, including the inclusion of additional input variables, fine-tuning model parameters, and expanding the training dataset. This study underscores the critical role of selecting appropriate optimization algorithms for enhancing the accuracy of LSTM models in forecasting volatile financial time-series data, particularly for currency exchange rates
Geographically Weighted Regression Modeling Using Fixed and Adaptive Kernel Weights for the Human Development Index Case in West Java Province: Pemodelan Regresi Berbobot Geografis Menggunakan Bobot Kernel Tetap dan Adaptif untuk Studi Kasus Indeks Pembangunan Manusia di Provinsi Jawa Barat Karin Karin; Alwan Fadlurohman; Dannu Purwanto
Journal of Data Insights Vol 3 No 2 (2025): Journal of Data Insights
Publisher : Department of Sains Data UNIMUS Universitas Muhammadiyah Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jodi.v3i2.887

Abstract

This study aims to analyze the factors influencing the Human Development Index (HDI) in West Java Province using the Geographically Weighted Regression (GWR) approach. The independent variables used in this study are the Open Unemployment Rate (TPT), School Participation Rate for ages 16–18 (APS_16_18), Population Density, and Gross Regional Domestic Product per Capita (PPK). The modeling was carried out by comparing various kernel functions, namely Gaussian, Bisquare, and Tricube, as well as two bandwidth approaches: fixed and adaptive. The results indicate that the GWR model with a Gaussian kernel and a fixed bandwidth approach provides the best performance based on the lowest AIC value. Compared to the classical Ordinary Least Squares (OLS) model, the GWR model offers a better explanation of spatial variation in HDI across the study area. Although the GWR model was not statistically significant overall based on the ANOVA test, local analysis showed that the variables TPT and PPK had significant effects in all districts and cities, while APS_16_18 and Population Density were not significant in any region. These findings demonstrate that the GWR model is capable of capturing spatial heterogeneity that is not detected by the global regression model.
Implementasi Teknologi Ramah Lingkungan untuk Menunjang Sektor Pertanian di Desa Margohayu Karangawen Demak M. Al Haris; Dannu Purwanto; Ali Imron; RA. Qonita Syalsabilla Handayani; Arya Praditya
LOSARI: Jurnal Pengabdian Kepada Masyarakat Vol. 6 No. 2 (2024): Desember 2024
Publisher : LOSARI DIGITAL

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53860/losari.v6i2.349

Abstract

Margohayu village is one of the regions in the Karangawen Subdistrict, Demak Regency, Central Java. Desa Margohayu has a population of 8,056, with the majority working as farmers. Currently, the irrigation of rice fields in Desa Margohayu still relies on fossil fuel-based energy, which gradually depletes and has environmental consequences. However, Desa Margohayu has significant potential to establish a self-sustaining energy system by harnessing solar energy. Sunlight can be converted into electricity through solar panels to power water pumps. Therefore, the Community Service Team from Universitas Muhammadiyah Semarang proposes an environmentally friendly and sustainable technology implementation in the agricultural sector through the Margo Mulyo Farmer Group in Desa Margohayu. The goal is to reduce the negative impact of fossil fuel usage that has been prevalent. The results of this initiative show that the Margo Mulyo Farmer Group gains knowledge and skills related to solar energy utilization. The implementation of this technology is expected to reduce agricultural costs, particularly in the irrigation process.
Analisis Peramalan Suhu Permukaan Bumi di Kota Semarang Menggunakan Regresi Nonparametrik dengan Estimator Deret Fourier Berdasarkan Penalized Least Square (PLS) Ihsan Fathoni Amri; Tiani Wahyu Utami; Dannu Purwanto; Alwan Fadlurohman; Ariska Fitriyana Ningrum; Saeful Amri
Jurnal Pengembangan Rekayasa dan Teknologi Vol. 10 No. 1 (2026): Mei (2026)
Publisher : Universitas Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26623/jprt.v10i1.14583

Abstract

Perubahan iklim global yang ditandai oleh peningkatan suhu permukaan menjadi isu penting, terutama di wilayah perkotaan dengan tingkat urbanisasi tinggi seperti Kota Semarang. Peningkatan suhu dapat memengaruhi kualitas lingkungan dan kenyamanan masyarakat, sehingga diperlukan pemodelan dan peramalan yang akurat untuk memahami pola perubahannya. Penelitian ini bertujuan membentuk model regresi nonparametrik menggunakan estimator deret Fourier dengan optimasi Penalized Least Square (PLS) serta meramalkan suhu permukaan di Kota Semarang. Parameter optimal ditentukan berdasarkan nilai Generalized Cross Validation (GCV) minimum. Hasil penelitian menunjukkan bahwa model terbaik diperoleh pada koefisien Fourier  dengan lambda optimal 0,00027 dan GCV minimum 0,81182. Model menghasilkan Mean Absolute Percentage Error (MAPE) sebesar 1,203717% dengan akurasi 98,7963%, yang termasuk kategori sangat baik. Hasil ini menunjukkan bahwa pendekatan deret Fourier berbasis PLS efektif dalam memodelkan dan meramalkan suhu permukaan di Kota Semarang.
Analisis Pengaruh Teknik Preprocessing terhadap Performa CNN pada Klasifikasi Citra Dataset CIFAR-10 Dannu Purwanto; Alwan Fadlurohman
Jurnal Pengembangan Rekayasa dan Teknologi Vol. 10 No. 1 (2026): Mei (2026)
Publisher : Universitas Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26623/jprt.v10i1.14651

Abstract

Penelitian ini menganalisis pengaruh teknik preprocessing citra terhadap performa Convolutional Neural Network (CNN) pada dataset CIFAR-10. Teknik yang dievaluasi meliputi normalisasi piksel, augmentasi data, dan filter median yang disusun dalam empat kondisi eksperimen: kontrol, normalisasi, normalisasi+augmentasi, serta normalisasi+augmentasi+median. Setiap kondisi dijalankan sebanyak lima kali menggunakan seed berbeda untuk memperoleh rerata dan standar deviasi. Hasil eksperimen menunjukkan bahwa kondisi kontrol memperoleh akurasi uji tertinggi sebesar 86,42% ± 0,37%, sedangkan normalisasi menghasilkan akurasi yang hampir setara sebesar 86,36% ± 0,28%. Penambahan augmentasi menurunkan akurasi uji menjadi 79,48% ± 2,80%, dan kombinasi normalisasi, augmentasi, serta median filter menghasilkan akurasi terendah sebesar 76,20% ± 2,88%. Temuan ini menunjukkan bahwa preprocessing tambahan yang diuji belum mampu meningkatkan akurasi CNN pada konfigurasi eksperimen ini. Penurunan terutama terjadi pada kelas hewan seperti bird, cat, dog, dan deer, yang mengindikasikan bahwa augmentasi dan median filter dapat mengurangi informasi visual penting pada citra beresolusi rendah.
Co-Authors - Tarsan Abdel Nasser Sharkawy Agustiyar Agustiyar Ahmad Amrullah B Alfidha Rahmah Ali Imron Ali Imron Alwan Fadlurohman Amanda, Qorry Amelia Kusuma Wardani Amri, Saeful Anggia Ersa Pratiwi Annisa Fadhilah Permatasari Ariska Fitriyana Ningrum Arya Praditya Basrowi, Ray Wagiu Dhani, Oktaviana Rahma Fauzi, Fatkhurokhman Fitri Diana Musa Haryani, Deby Aprilia Ihsan Fathoni Amri Karin Karin Lein, Raymond Bolly Linda Puspitasari M. Al Haris Maryam, Adiva Kalila Miftah Nur Zaidan Miftakhul Haris Najwa Fatin Siddiq Novia Yunanita Prastyo, Ikwan Pratama, Rizky Adi Prizka Rismawati Arum Qonita Syalsabilla Handayani Qorry Amanda RA. Qonita Syalsabilla Handayani Rahma Nurmalita Salsabila Mutiara Yunus Samikoh Ulinuha Sitti Sahara Sofa, Yulia Ratna Soffi Amalia Nur Kholifah Tiani Wahyu Utami Wardani, Amelia Kusuma Yan Nazala Bisoumi Yuli Puspita Devi