cover
Contact Name
Dr. Muhammad Ahsan
Contact Email
muh.ahsan@its.ac.id
Phone
+6281331551312
Journal Mail Official
inferensi.statistika@its.ac.id
Editorial Address
Department of Statistics Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember (ITS) Kampus ITS Keputih Sukolilo Surabaya Indonesia 60111
Location
Kota surabaya,
Jawa timur
INDONESIA
Inferensi
ISSN : 0216308X     EISSN : 27213862     DOI : http://dx.doi.org/10.12962/j27213862
The aim of Inferensi is to publish original articles concerning statistical theories and novel applications in diverse research fields related to statistics and data science. The objective of papers should be to contribute to the understanding of the statistical methodology and/or to develop and improve statistical methods; any mathematical theory should be directed towards these aims; and any approach in data science. The kinds of contribution considered include descriptions of new methods of collecting or analysing data, with the underlying theory, an indication of the scope of application and preferably a real example. Also considered are comparisons, critical evaluations and new applications of existing methods, contributions to probability theory which have a clear practical bearing (including the formulation and analysis of stochastic models), statistical computation or simulation where the original methodology is involved and original contributions to the foundations of statistical science. It also sometimes publishes review and expository articles on specific topics, which are expected to bring valuable information for researchers interested in the fields selected. The journal contributes to broadening the coverage of statistics and data analysis in publishing articles based on innovative ideas. The journal is also unique in combining traditional statistical science and relatively new data science. All articles are refereed by experts.
Articles 9 Documents
Search results for , issue "Vol 7, No 3 (2024)" : 9 Documents clear
Hybrid CNN-SVM with Borderline SMOTE for Imbalance Class Cabbage Plants Sovia, Nabila Ayunda; Wardhani, Ni Wayan Surya; Sumarminingsih, Eni
Inferensi Vol 7, No 3 (2024)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v7i3.20514

Abstract

Cabbage farming is highly vulnerable to diseases and pests, leading to substantial yield losses if not properly managed. Traditional diagnostic methods, reliant on manual assessment, are often time-consuming and inaccurate. This study introduces a hybrid approach combining Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) to address these challenges, specifically focusing on improving classification accuracy in imbalanced cabbage image datasets. CNNs are leveraged for their powerful feature extraction, while SVM, optimized using a One-vs-All strategy, enhances multi-class classification. To handle data imbalance, Borderline SMOTE (Synthetic Minority Over-sampling Technique) is applied, generating synthetic samples to balance underrepresented classes. The SqueezeNet architecture is employed for feature extraction, with SVM hyperparameters fine-tuned via grid search. Results demonstrate that the integration of CNN, SVM, and Borderline SMOTE significantly improves classification performance, particularly for minority classes, achieving an accuracy of 99%. This approach offers a more reliable and efficient tool for early detection of cabbage diseases and pests, contributing to better agricultural management and reduced crop losses.
Modeling Stunting Prevalence in Indonesia Mixed Spline Truncated and Fouries Series Nonparametric Regression Husain, Hartina; Irmayani, Irmayani; Rahman, Andi Oxy Raihan Machikami
Inferensi Vol 7, No 3 (2024)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v7i3.20518

Abstract

Stunting is a condition of failure to grow in children that occurs due to malnutrition chronic so that the child's height is shorter compared to his age. This research aims to model the factors that influence the prevalence of stunting in Indonesia based on a literature study using mixed spline truncated and fourier series nonparametric regression method. Data used is secondary data regarding the prevalence of stunting and several suspected factors influencing it, namely the percentage of the population with health insurance and the percentage of the population who smoked last month (Age ≥ 15 Years). Data was sourced from publications from the Ministry of Health and Badan Pusat Statistik (BPS) in 2022. The results show that the model combines a spline truncated component with one knot and a fourier series component with one oscillation , resulting in  a minimum Generalized Cross Validation (GCV) Value of  34.46 and an Mean Square Error (MSE) of 4.89.
Data Analysis of Diabetes Mellitus with Joint Modeling Method Sofro, A'yunin; Mukaromah, Muizzatul; Khikmah, Khusnia Nurul
Inferensi Vol 7, No 3 (2024)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v7i3.20519

Abstract

Diabetes mellitus is a dangerous disease that requires long-term medical treatment. The cause of this disease is high blood sugar levels. If not treated immediately, complications will occur and even cause death. The data is taken from the Indonesia Family Life Survey (IFLS). IFLS is a longitudinal measurement that is performed repeatedly every five years. More data is needed for repeated measures. Therefore, this research needs to be done to accommodate the missing data, and it is assumed that it is missing at random (MAR). This study aims to analyze the causative factors that are thought to affect the recovery time of patients with diabetes mellitus using the joint modeling method. This model is a relationship between event time data and repeated measurement data. The joint modeling method uses a linear mixed model for longitudinal measurements and a Cox proportional hazard model for survival. The variables were taken from IFLS4 and IFLS5 data with 293 observations: measurement time, treatment history, gender, comorbidities, and complications. The results in this study obtained a significant influence, namely the variables of measurement time, gender, and complications, on the recovery time of patients with diabetes mellitus. With the reduced measurement time, the patient has a lower chance of recovering 8.7184 times. The variables of gender also have a lower possibility of recovery of 9.1032 times, respectively.
Estimation of Paddy Productivity at Subdistrict Level using Geoadditive Small Area Estimation Model in Ponorogo Regency Maulana, Arswenda Putra; Prasetyo, Rindang Bangun
Inferensi Vol 7, No 3 (2024)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v7i3.20505

Abstract

Paddy is the most important food crop in the world and it is the source of food needed by more than half of the population on a global scale. However, the world is experiencing the threat of a food crisis, so the Indonesian government continues to be committed to increasing national paddy production and ensuring food sufficiency in the country by implementing food self-sufficiency programs in each region. Paddy productivity data can be used as one of the government's benchmarks to assess the success of the food self-sufficiency program, but BPS-Statistics Indonesia only provides data on paddy productivity up to the district/cities level. Therefore, this study aims to estimate paddy productivity at sub-district level using the Geo-SAE method. Based on the research results, the estimation of the average paddy productivity in Ponorogo Regency in 2022 using Geo-SAE was obtained at 5.8 tons/ha and resulted in a smaller RSE value compared to the direct estimation at sub-district level. This indicates that the Geo-SAE method has better precision than the direct estimation method. Meanwhile, additional result from estimation of paddy productivity shows that in Ponorogo Regency in 2022 there is a large rice surplus. Therefore, it can be said that Ponorogo Regency is experiencing a very good food sufficiency condition.
Effectiveness of GPCA in Reducing Data Dimensions and its Application to Human Development Dimension Indicators Data Zubedi, Fahrezal; Sumertajaya, I Made; Notodiputro, Khairil Anwar; Syafitri, Utami Dyah
Inferensi Vol 7, No 3 (2024)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v7i3.21506

Abstract

Analysis of human development growth at the regency/city level is challenging because the data is high-dimensional, indicators are correlated, and the regencies/cities are correlated. In this study, we propose a Generalized Principal Component Analysis to analyze human development growth by reducing the dimensions of regency/city and indicator. Thus, human development growth at the regency/city level is analyzed using the GPCA results in Biplot to describe each regency/city and its indicators. This study aims to evaluate GPCA in reducing the dimensionality of data whose observations are correlated, and indicators are correlated through simulation and empirical study; to analyze the growth of human development at the regency/city level based on the results of GPCA-Biplot. This research shows that GPCA works well in reducing data dimensions from correlated observations and correlated variables. Based on the results of the GPCA-Biplot visualization, the growth of human development in the Nduga regency from 2019 to 2022 showed significant fluctuations. Although some indicators show progress, especially in 2021, significant challenges remain. In the same way, the growth of human development in each regency/city can be analyzed. Thus, government policy focuses on real problems in the field.
Forecasting Tourist Visits During The Covid-19 Pandemic and MotoGP Events Using The Sarima Method Soraya, Siti; Rahima, Phyta; Primajati, Gilang; Nurhidayati, Maulida; Fajri, Mohammad
Inferensi Vol 7, No 3 (2024)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v7i3.20139

Abstract

The 5.0 era has made the tourism sector one of the measures of the economic welfare of a region, such as in West Nusa Tenggara (NTB). This is proven by the presence of various types of MSMEs and their innovations and the increasing number of tourist visits to NTB from year to year. The condition of the tourism sector certainly has a positive impact on increasing NTB's economic growth and indirectly on optimizing existing infrastructure. However, extraordinary events such as the earthquake in 2018 and the COVID-19 pandemic resulted in the decline of NTB tourism visits. Then tourist visits in NTB increased again with the holding of the MotoGP  Event. The purpose of this study is to forecast the number of tourist visits to NTB. This is very much needed in helping the government to prepare appropriate policies if there is a possibility of a surge in tourist visits in the following years. As well as anticipating if there are other extraordinary events such as earthquakes or global cases. The method used in this study is the Seasonal Autoregressive Integrated Moving Average (SARIMA) Method. The stages in this method are by describing data, preprocessing data, identifying stationary models, estimating models, selecting the best SARIMA model and forecasting with the obtained model to forecasting the next desired period. The results of research that have been conducted state that in 2023 to 2024 the number of tourists visiting NTB continues to increase both domestically and abroad. It is hoped that the results of this research will be able to provide information and contribute knowledge and consideration materials in policy making in the development of NTB government tourism.
Negative Binomial Regression Analysis of Factors Influencing Stunting Cases in Central Lombok Regency Putri Ananda, Elma Yulia; Annas, Suwardi; Ihsan, Hisyam; Sukarna, Sukarna; Aswi, Aswi
Inferensi Vol 7, No 3 (2024)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v7i3.21436

Abstract

Poisson regression is commonly used to model count data, relying on the crucial assumption of equidispersion, where the mean and variance are equal. However, this assumption is often violated in real-world data, which can exhibit overdispersion or underdispersion. When this occurs, the standard Poisson model becomes unsuitable, leading to biased and inaccurate parameter estimates. To address overdispersion in count data, Negative Binomial Regression (NBR) is a viable alternative, as it incorporates an additional parameter to account for variability greater than the mean. Stunting, a condition characterized by significantly impaired growth in infants, has been a primary concern for the Indonesian government during the 2019-2024 period, particularly in Central Lombok district. Reducing stunting rates is critical to ensuring an optimal quality of life for future generations. Despite extensive research on stunting, the application of NBR to analyze factors influencing stunting cases in Central Lombok Regency has not yet been explored. This study aims to implement the NBR model to identify the determinants of stunting in Central Lombok. Data were collected from 29 community health centers (PUSKESMAS) in Central Lombok. The findings indicate that an increase in the number of malnourished toddlers is associated with a corresponding rise in stunting cases. Similarly, a higher prevalence of low-birth-weight infants is linked to an elevated incidence of stunting.
Topic Modelling of Merdeka Belajar Kampus Merdeka Policy Using Latent Dirichlet Allocation Thamrin, Sri Astuti; Rezki, Nurul; Siswanto, Siswanto
Inferensi Vol 7, No 3 (2024)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v7i3.20602

Abstract

Topic modeling is the process of representing the topics discussed in text documents. In the current era of internet technology development, digital data is growing increasingly large, including tweet data from Twitter. This research aims to obtain topic modeling related to the Merdeka Belajar Kampus Merdeka policy on Twitter, which has been classified into positive and negative sentiments. The topic modeling method used is Latent Dirichlet Allocation (LDA). This method is for summarizing, clustering, connecting, or processing data from a list of topics. The data used in this research are tweets with the keyword "Kampus Merdeka" uploaded on Twitter. A total of 1579 tweets with these keywords were classified into 648 tweets and 931 tweets, respectively, with positive and negative sentiments. Each tweet with positive and negative sentiment produces 5 topics with parameter values α and β of 0.1. The coherence value in topic modeling for tweets with a positive sentiment (0.44) is more significant than for tweets with a negative sentiment (0.38) and represent for drawing conclusions about topics based on relationship between keywords in negative sentiment is more challenging compared to those in positive sentiment to the Merdeka Belajar Kampus Merdeka policy on Twitter.
Analysis of Text Mining Clustering on Suara Surabaya Crime Report with DBSCAN Neural Network Autoencoder Algorithm Koesnadi, Grace Lucyana; Anggriawan, Muhammad Rizal; Zuleika, Talitha; Putra, Mochamad Rasyid Aditya; Aldawiyah, Najwa Khoir; Mardianto, M Fariz Fadillah
Inferensi Vol 7, No 3 (2024)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v7i3.20765

Abstract

Criminality, or crime, is a behavior that violates the law or is contrary to applicable values and norms. A high number of criminal behaviors criminal behaviors in a community significantly impacts its social conditions, leading to a decrease in welfare, unrest, and material losses that pose a threat to an individual's life. This study examines text mining on crime report data from Suara Surabaya using the DBSCAN clustering method and the Neural Network Autoencoder. The neural network autoencoder algorithm effectively reduces the data dimension, with an input dimension of 300 and an encode dimension of 64. Clustering analysis using the DBSCAN method based on the silhouette coefficient value criterion resulted in three clusters, with cluster 1 dominating the report. The clustering results show essential patterns in complaint reports, and LDA analysis reveals critical topics in the report. Cluster 0 shows a diversity of reports focusing on motor loss, interaction with homes or properties, and people's entry into homes. Cluster 1 is more focused on the loss of vehicles, both cars and motorcycles, with specific details such as vehicle color, number, brand, and related transactions or social interactions. Meanwhile, cluster 2 focuses on reports related to interactions with police stations and information on the location of incidents. This text mining approach to community crime report data not only improves analysis accuracy and efficiency, but also provides essential information that can support efforts to handle and prevent crime.

Page 1 of 1 | Total Record : 9