Claim Missing Document
Check
Articles

Found 36 Documents
Search

Estimasi Laju Penurunan Muka Tanah DKI Jakarta Tahun 2022 Menggunakan Metode Ordinary Kriging Nabilah Sofieyanti; Dwi Agustin Nuriani Sirodj
Bandung Conference Series: Statistics Vol. 4 No. 2 (2024): Bandung Conference Series: Statistics
Publisher : UNISBA Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/bcss.v4i2.15083

Abstract

Abstract. Land subsidence in DKI Jakarta has become a serious issue with the potential to cause environmental damage, especially in terms of infrastructure damage and an increased risk of flooding. Monitoring and observing the rate of land subsidence need to be conducted regularly to prevent more severe impacts. However, due to limitations in budget, time, and resources, spatial interpolation methods like Ordinary Kriging can be used to estimate the rate of land subsidence in unsampled locations. The data used in this study were secondary data on the rate of land subsidence at 100 locations in DKI Jakarta in 2022. In this research, the data were assumed to be stationary. The results show that the best theoretical semivariogram model is the Spherical model because it has the smallest RMSE value compared to the Exponential and Gaussian models. The Ordinary Kriging method was successfully applied to estimate the rate of land subsidence in unsampled locations in 2022. According to the estimates, the highest rate of land subsidence occurred in the Duri Kosambi area of West Jakarta, while the lowest rate occurred in the Tangki area of West Jakarta. These interpolation results can serve as a basis for more effective mitigation, control, and prevention measures. Abstrak. Penurunan muka tanah di DKI Jakarta menjadi masalah serius yang berpotensi menimbulkan kerusakan lingkungan terlebih pada rusaknya infrastruktur dan meningkatkan resiko banjir. Pengamatan dan pemantauan laju penurunan muka tanah perlu dilakukan secara teratur untuk mencegah dampak yang lebih buruk. Akan tetapi, karena adanya keterbatasan biaya, waktu, dan sumber daya yang tidak sedikit. Metode interpolasi spasial seperti Ordinary Kriging dapat dilakukan untuk mengestimasi laju penurunan muka tanah pada lokasi yang tidak tersampel. Data yang digunakan adalah data sekunder tentang laju penurunan muka tanah pada 100 titik lokasi di DKI Jakarta tahun 2022. Pada penelitian ini, data diasumsikan bersifat stasioner. Hasil penelitian menunjukkan bahwa model semivariogram teoritis yang terbaik adalah model Spherical karena memiliki nilai RMSE terkecil daripada model Eksponensial dan Gaussian. Metode Ordinary Kriging berhasil dilakukan untuk estimasi laju penurunan muka tanah pada lokasi tidak tersampel tahun 2022. Dari hasil estimasi, laju penurunan muka tanah terbesar yaitu 0,0529 cm/tahun terjadi di daerah Duri Kosambi Jakarta Barat, sementara laju penurunan terkecil yaitu 0,0306 cm/tahun di daerah Tangki Jakarta Barat. Hasil interpolasi ini dapat menjadi dasar untuk tindakan mitigasi, pengendalian, dan pencegahan yang lebih efektif.
Adaptasi Indonesia Bergen Social Media Addiction Scale Sumaryati, Indri Utami; Sirodj, Dwi Agustin Nuriani; Gadama, Melsan
Jurnal Online Psikogenesis Vol 12 No 1 (2024): June
Publisher : Fakultas Psikologi Universitas YARSI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24854/jps.v12i1.3994

Abstract

Empirical background on emphasizing behavioral addiction becoming more important nowadays. Therefore the measurement toward behavioral addiction become necessary. Social media were online activities and became popular during 10 years earlier. Empirical data shown that media social user performed excessive use of media social that might be lead to addiction. This research aimed to performed measurement adaptation toward Bergen Social Media Addiction scale (BSMAS). The adaptation process were based on the International Test Commision (ITC). Multistage sampling were performed in resulting 483 samples. Statistical analysis conducted were Confirmatory Factor Analysis (CFA), and the result were CR value (0.91)> 0,70 and the VE value (0.65) > 0,50, means the measurement have fulfilled internal consistency and p-value of RMSEA, CFI, GFI and AGFI were fulfilling the criterias . Keywords: Addiction, CFA, Measurement adaptation, Social media.
Penerapan Support Vector Machine untuk Klasifikasi Opini Masyarakat Terhadap Isu Bullying Noor, Farras Rachmanisa; Sirodj, Dwi Agustin Nuriani
Jurnal Riset Statistika Volume 4, No. 1, Juli 2024, Jurnal Riset Statistika (JRS)
Publisher : UPT Publikasi Ilmiah Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/jrs.v4i1.3877

Abstract

Abstract. Support Vector Machine (SVM) concept is explained as an attempt to find the best hyperplane (separation function) that serves as a separator of two classes in the input space by maximizing the distance between classes (Alhaq, et al., 2021). This algorithm has proven to have good performance as a classification method, by producing a fairly good model accuracy value. This analysis process uses the Python programming language, the keywords used for crawling tweet data are a combination of the words bully/bullying and school/elementary school/junior high/high school, with a data retrieval period from November 1, 2022 to June 30, 2023, the results obtained are 13,918 tweets. Then preprocessing is carried out, at this stage the data that passes the classification process is 2,519 tweets with the number of positive sentiments 1,268 tweets and negative sentiments 1,251 tweets. Furthermore, the division of training and testing data with a ratio of 80:20. The application of the SVM algorithm produces an accuracy value of 84.5%, meaning that this method can predict the sentiment of the bullying issue tweet sentence with the category of good classification (Gorunescu, 2011), precision 84.7%, recall 82.9% and F1-score 83.8%. Overall, this model works well and consistently for the case of tweet data. Abstrak. Support Vector Machine (SVM) dijelaskan sebagai usaha mencari hyperplane (fungsi pemisah) terbaik yang berfungsi sebagai pemisah dua buah kelas pada input space dengan memaksimalkan jarak antar kelas (Alhaq, et al., 2021). Algoritma ini sudah terbukti memiliki kinerja yang baik sebagai metode klasifikasi, dengan menghasilkan nilai akurasi model yang cukup baik. Proses analisis ini menggunakan bahasa pemrograman Python, kata kunci yang digunakan untuk crawling data tweet yaitu kombinasi kata bully/bullying dan sekolah/SD/SMP/SMA, dengan periode pengambilan data dari 1 November 2022 hingga 30 Juni 2023, hasilnya diperoleh 13.918 tweet. Kemudian dilakukan preprocessing, pada tahap ini data yang lolos dilanjutkan proses klasifikasi sebanyak 2.519 tweet dengan jumlah sentimen positif 1.268 tweet dan sentimen negatif 1.251 tweet. Selanjutnya pembagian data training dan testing dengan perbandingan 80:20. Penerapan algoritma SVM menghasilkan nilai accuracy sebesar 84.5%, artinya metode ini dapat melakukan prediksi sentimen dari kalimat tweet isu bullying dengan kategori good classification (Gorunescu, 2011), precision 84.7%, recall 82.9% dan F1-score 83.8%. Secara keseluruhan model ini bekerja dengan baik dan konsisten untuk kasus data tweet.
Pemodelan Generalized Poisson Regression untuk Mengatasi Overdispersi Kasus Gizi Buruk Balita Syalsa Navi Yusnita; Dwi Agustin Nuriani Sirodj
Jurnal Riset Statistika Volume 5, No. 1, Juli 2025, Jurnal Riset Statistika (JRS)
Publisher : UPT Publikasi Ilmiah Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/jrs.v5i1.6434

Abstract

Abstract. Poisson regression is a statistical model used to analyze the relationship between a dependent variable, which consists of count data following a Poisson distribution, and one or more independent variables. This model assumes equidispersion, meaning the variance of the response variable is equal to its mean. However, in some cases, this assumption is violated, leading to overdispersion, where the variance is greater than the mean. As a result, Poisson regression may not be appropriate for modeling data with overdispersion, as the estimated standard errors tend to underestimate the regression parameters, resulting in inaccurate conclusions. Generalized Poisson Regression (GPR) is an extension of Poisson regression that introduces a dispersal parameter to address overdispersion. This study applies GPR to to analyze the case of malnutrition in children under five in Central Java Province in 2022. The analysis reveals the presence of overdispersion in the malnutrition data, as well as several factors that negatively affect the number of malnourished children. These factors include complete immunization, exclusive breastfeeding, low birth weight, access to safe drinking water, and access to adequate sanitation. The results suggest that improving these factors could reduce the number of malnourished children. Based on the AIC value of 382.7872, the GPR model is shown to be more effective than the Poisson model in modeling malnutrition cases in children under five across the districts and cities of Central Java in 2022. Abstrak. Regresi Poisson adalah model statistik yang digunakan untuk menganalisis hubungan antara variabel dependen, yang terdiri dari data hitung yang mengikuti distribusi Poisson, dengan satu atau lebih variabel independen. Model ini mengasumsikan equidispersi yaitu dimana variansi dari variabel respon harus sama dengan rata-ratanya. Namun, dalam beberapa kasus asumsi ini dapat dilanggar yang mengarah pada overdispersi, di mana variansi lebih besar dari rata-rata. Akibatnya, regresi Poisson tidak cocok untuk memodelkan data dengan overdispersi, karena galat baku yang dihasilkan akan menyebabkan dugaan parameter regresi cenderung lebih rendah dari seharusnya yang dapat menghasilkan kesimpulan tidak akurat. Generalized Poisson Regression (GPR) adalah pengembangan dari regresi Poisson yang memperkenalkan parameter dispersi untuk mengatasi masalah overdispersi. Penelitian ini mengaplikasikan GPR untuk menganalisis kasus gizi buruk pada balita di Provinsi Jawa Tengah pada tahun 2022. Analisis ini mengungkapkan adanya overdispersi pada data gizi buruk, serta beberapa faktor yang mempengaruhi jumlah balita yang menderita gizi buruk. Faktor-faktor tersebut meliputi imunisasi lengkap, ASI eksklusif, berat badan lahir rendah, akses terhadap air minum yang aman, dan akses terhadap sanitasi yang memadai. Hasil penelitian menunjukkan bahwa perbaikan faktor-faktor ini dapat mengurangi jumlah balita yang menderita gizi buruk. Berdasarkan nilai AIC sebesar 382.7872, model GPR terbukti lebih efektif dibandingkan dengan model Poisson dalam memodelkan kasus gizi buruk pada balita di kabupaten/kota di Provinsi Jawa Tengah tahun 2022.
MODELING THE INCIDENCE OF MALNUTRITION IN BOGOR REGENCY USING ZERO-INFLATED NEGATIVE BINOMIAL MIXED EFFECT MODEL Sirodj, Dwi Agustin Nuriani; Sadik, Kusman; Kurnia, Anang
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 18 No 2 (2024): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol18iss2pp0961-0972

Abstract

Modeling response variables in the form of count data generally uses a model based on the Poisson distribution. However, some conditions, such as the presence of excess zero, can be found in the data that result in overdispersion, which will have an impact on the resulting variance in the model. In this paper, three approaches, namely the Poisson Mixed Model, the Negative Binomial (NB) Mixed Model, and the Zero-Inflated Negative Binomial (ZINB) Mixed Model, are used to model the incidence of malnutrition in Bogor Regency. The data used in this study are secondary data sourced from the West Java open data website. Based on the results of data analysis, it appears that the ZINB Mixed Model method is a method capable of accommodating random effects, overdispersion, and excess zero in modeling malnutrition in Bogor Regency. Variables that significantly affect the occurrence of malnutrition cases in villages in Bogor Regency include the Number of Children Weighed Routinely Every Month, Number of Children Measured for Length and Height Twice a Year, Number of Children under 12 Months Old Who Received Complete Basic Immunization, Number of Posyandu (Integrated Health Post), and Number of Parents/Caregivers Participating in Monthly Parenting (PAUD).
Perbandingan Kerja Binomial GLMM Tree dan BIMM Forest untuk Memodelkan Status Bekerja Penduduk Sirodj, Dwi Agustin Nuriani; Notodiputro, Khairil Anwar; Sartono, Bagus
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 11 No 1: Februari 2024
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.20241117531

Abstract

Model prediksi berbasis pada pohon keputusan saat ini banyak dikembangkan di berbagai bidang. Pengembangan metode yang dilakukan diantaranya memasukkan pengaruh acak ke dalam model.  Generalized linier mixed model (GLMM) Tree menjadi salah satu model yang dapat mengakomodasi adanya pengaruh acak dan dilakukan dengan metode partisi rekursif hanya saja waktu komputasi yang dibutuhkan relatif lebih lama. Selanjutnya metode alternatif lainnya adalah Binary Mixed Model (BiMM) Forest yang menggabungkan prinsip kerja Bayesian GLMM dan Random Forest. Dari kedua metode yang akan digunakan maka permasalahan yang dihadapi adalah bagaimana kinerja dari metode GLMM Tree dan BiMM Forest jika diterapkan untuk klasifikasi status bekerja penduduk di Kabupaten Bogor dan Kabupaten Pangandaran. Dari hasil analisis tampak bahwa metode BiMM Forest memiliki kinerja yang lebih baik di bandingkan dengan GLMM Tree untuk kedua daerah. Selain itu ditunjukkan pula bahwa peubah yang penting dalam proses klasifikasi status bekerja penduduk di Kabupaten Bogor dan Kabupaten Pangandaran adalah peubah terkait aspek pendidikan, sosial, dan ekonomi.
Recycling Solid Waste of Coconut Oil Industry: A Response Surface-Goal Programming Approach Dwi Agustin Nuriani Sirodj; Ivan Gunawan
Jurnal Optimasi Sistem Industri Vol. 19 No. 2 (2020): Published in October 2020
Publisher : The Industrial Engineering Department of Engineering Faculty at Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/josi.v19.n2.p111-121.2020

Abstract

Waste minimization is a key success factor to achieve sustainability, including in the edible oil industry. One type of solid waste produced substantially in this industry is spent bleaching earth (SBE), which comes from a mixture of bleaching earth (BE) and activated carbon (CA) used in the edible oil refining process. SBE that is recycled through a heating process is known as heat regenerated SBE (HRSBE). The process is influenced by two factors as stated in previous studies: temperature and time. In the current study, we report the results of experiments to find the optimal combination of temperature and time in restoring the absorbent quality of SBE by observing four quality parameters: colors (red and yellow), Free Fatty Acid (FFA), and Peroxide Value (PV). The current study uses Response Surface Methodology (RSM) to design the experiments and to find the equations of the relationship between the factors for each response; as well as Goal Programming (GP) to find the most optimal combination of factors in order to achieve aggregated quality targets. The findings show that 3.414 hours of heating at a temperature of 151.64oC allow HRSBE to produce coconut oil in accordance with the expected quality targets.
Spatial Interpolation of the Probability of Mercury Threshold Exceedance Using Indicator Kriging Zhahirulhaq, Mufdhil Afta; Sirodj, Dwi Agustin Nuriani
Parameter: Jurnal Matematika, Statistika dan Terapannya Vol 4 No 3 (2025): Parameter: Jurnal Matematika, Statistika dan Terapannya
Publisher : Jurusan Matematika FMIPA Universitas Pattimura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/parameterv4i3pp395-408

Abstract

Indicator Kriging (IK) is a spatial interpolation method used to estimate the probability that a variable exceeds a specified threshold. This study applies IK to assess the probability of mercury (Hg) concentrations exceeding environmental thresholds in river systems across DKI Jakarta. Given the skewed and non-normally distributed nature of mercury data, IK was selected due to its robustness in handling non-parametric data and its sensitivity to extreme values. Mercury concentration measurements were first transformed into binary indicator data based on a predefined threshold. An experimental semivariogram was then computed to analyze the spatial dependence of the indicator values, followed by the fitting of theoretical semivariogram models (Gaussian, Spherical, and Exponential). The best-fitting model was selected using the Leave-One-Out Cross-Validation (LOOCV) approach, with the Spherical model yielding the lowest root mean square error (RMSE). The final probability map generated through IK reveals five unsampled locations with a probability greater than 0.5 of mercury concentration exceeding the threshold: two located along the Ciliwung River and three along the Sunter River. These findings highlight critical zones requiring monitoring and support the use of IK as an effective geostatistical tool for environmental risk assessment of heavy metal contamination in urban river systems.
Integrating Support Vector Regression and Kriging in Spatial Interpolation of Statistical Seismicity Parameters Sirodj, Dwi Agustin Nuriani; Aidi, Muhammad Nur; Sartono, Bagus; Syafitri, Utami Dyah; Pranata, Bayu
Indonesian Journal of Geography Vol 57, No 3 (2025): Indonesian Journal of Geography
Publisher : Faculty of Geography, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijg.102153

Abstract

Spatial interpolation methods, such as Inverse Distance Weighting (IDW) and kriging, are commonly used in various fields. In Kriging method, semivariogram fitting is an important step, where empirical data are used to derive a theoretical model. However, when the known theoretical semivariogram model does not provide a satisfactory fit, the bias in the estimated values is increased. To address this limitation, Support Vector Regression (SVR) can be used to model the empirical semivariogram with a machine-learning method. This method has been applied in ordinary kriging interpolation for semivariogram fitting to estimate parameters related to the potential occurrence of earthquake. Specifically, the calculated parameters, based on the Gutenberg-Richter law, include the seismic activity (a-value) and rock fragility (b-value) in the Sumatera region. The results showed that SVR can model the empirical semivariogram better than the theoretical. The integration of SVR-Ordinary Kriging provides the best performance compared to other methods, such as IDW, with the smallest RMSEP values for both the b-value and a-value measuring 0.1378 and 0.7423, respectively. Aceh and Mentawai Islands tend to show low a and b values, suggesting that these areas are more vulnerable to earthquake with large magnitudes.
Identification of Earthquake Prone Zones in Sumatra using Density Based Spatial Clustering of Applications with Noise Dwi Agustin Nuriani Sirodj; Muhammad Nur Aidi; Bagus Sartono; Utami Dyah Syafitri; Bayu Pranata
CAUCHY: Jurnal Matematika Murni dan Aplikasi Vol 10, No 2 (2025): CAUCHY: JURNAL MATEMATIKA MURNI DAN APLIKASI
Publisher : Mathematics Department, Maulana Malik Ibrahim State Islamic University of Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/cauchy.v10i2.36120

Abstract

This study investigates the spatial distribution of earthquakes in Sumatra using the DBSCAN clustering algorithm applied to seismic data spanning 1 January 2000 to 31 December 2023. The analysis identified two distinct seismic clusters: one in the northern region (Aceh and North Sumatra) and another in the southern region (Lampung, Bengkulu, and West Sumatra), while several events in central areas were classified as noise. Cluster validity assessment confirmed that the identified groups are compact and well separated, reflecting meaningful seismotectonic segmentation. Statistical testing further revealed significant differences in earthquake depth and magnitude between the clusters, supporting the robustness of the findings. Notably, the southern cluster corresponds to the Mentawai Fault system, whereas the northern cluster aligns with the subduction zone and the Sumatran Fault. DBSCAN proved particularly effective in this context as it can capture clusters of arbitrary shapes, consistent with the complex geological structures governing seismicity in Sumatra.