Claim Missing Document
Check
Articles

Found 37 Documents
Search

Random Forest Method Approach to Customer Classification Based on Non-Performing Loan in Micro Business Muhajir, Muhammad; Widiastuti, Julia
JOIN (Jurnal Online Informatika) Vol 7 No 2 (2022)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v7i2.842

Abstract

This study aims to classify potential customers’ characteristics based on non- performing loans through the random forest method. This research uses data obtained from Syariah Mandiri Bank branch in Jambi, which includes data on micro-financing customers in years 2016–2020. The random forest method is used for analysis. The novelty of this work is that, unlike existing researches that used other soft-computing methods, we employ Random Forest method, specifically using an imbalanced class sampling technique. The obtained results show that credit risk can be estimated by taking into account factors such as age, monthly installments, margin, price of insurance, loan principal, occupation, and long installments. The research results indicate that the sensitivity, precision, and G-mean value increase compared to using the original data. Random forest with oversampling technique has the high Area Under the ROC Curve score that is equal to 66.69%.
Identifying malaria disease through red-blood microscopic image with XGBoost and random forest methods Fajriyah, Rohmatul; Muhajir, Muhammad; Abdullah, Ahmad Hussain; Ayu, Devina Gilar; Rahman, Iqbal Fathur
Bulletin of Applied Mathematics and Mathematics Education Vol. 4 No. 2 (2024)
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/bamme.v4i2.11740

Abstract

Blood cells that flow in the human body provide information to diagnose a disease. The information provided can be obtained through images of these blood cells using image processing techniques. Malaria is a very deadly disease and can affect everyone. Patients with malaria will experience anaemia because the red blood cells or erythrocytes are contaminated with plasmodium. This study offers an alternative solution to malaria disease identification through the image classification of red blood cells, by applying image processing and image classification methods with XGBoost and random forest. The research was conducted using the R programming language in RStudio and Python. The accuracy of XGBoost and random forest methods were 71.26% and 77.58%, respectively. Therefore, the random forest provided a better optimal classification model with higher accuracy. The model is used to build an application which is R web-based, RShiny. In practice, this application can be used by health workers in classifying patients based on red blood cell images such that the health centre would be easier to manage the existing patients.
Indonesian Inflation Forecasting with Recurrent Neural Network Long Short-Term Memory (RNN-LSTM) Hermansah; Muhajir, Muhammad; Canas Rodrigues, Paulo
Enthusiastic : International Journal of Applied Statistics and Data Science Volume 4 Issue 2, October 2024
Publisher : Universitas Islam Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20885/enthusiastic.vol4.iss2.art5

Abstract

This study forecasted inflation in Indonesia using the Recurrent Neural Network Long Short-Term Memory (RNN-LSTM) model, ideal for nonlinear, complex time series data. It evaluated the effects of different activation functions, such as Logistic, Gompertz, and Hyperbolic Tangent (tanh); and weight update methods, such as Stochastic Gradient Descent (SGD) and Adaptive Gradient (AdaGrad) on RNN-LSTM performance. Monthly inflation data from January 2005 to December 2023 underwent preprocessing, including normalization and autoregressive lag-based input selection. Model accuracy was assessed with Root Mean Squared Error (RMSE) and Symmetric Mean Absolute Percentage Error (SMAPE). The findings indicated that the RNN-LSTM model with the logistic activation function and SGD optimization achieved the highest accuracy, outperforming traditional models such as Exponential Smoothing (ETS), Autoregressive Integrated Moving Average (ARIMA), Feedforward Neural Network (FFNN), and Recurrent Neural Network (RNN). Additionally, optimal learning rate and epoch values were identified, enhancing model stability and precision. In conclusion, the study confirms that the RNN-LSTM model is effective for inflation forecasting when optimized with specific activation functions and optimization methods. It recommends further exploration of neuron configurations and alternative models, such as the Gated Recurrent Unit (GRU), to improve forecast accuracy.  
The Closure of Isbat For Polygamous Marriage on Legal Purpose Perspective Alhaidar, Nihrul Bahi; Muhajir, Muhammad; Dhuha, Syamsud
Al-Hukama': The Indonesian Journal of Islamic Family Law Vol. 13 No. 1 (2023): June
Publisher : Islamic Family Law Department, Sharia and Law Faculty, UIN Sunan Ampel Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15642/alhukama.2023.13.1.1-26

Abstract

After attendance, the enactment of the Supreme Court Circular (SEMA) Number 3 of 2018 answers the legal vacuum over isbat for Polygamous marriage. But in practice, the SEMA confuses its implementation. This study aims to analyze the application of polygamous marriage law in SEMA number 3 of 2018 and the juridical implications for justice, expediency, and legal certainty. This research includes normative legal research with statutory and conceptual approaches. Gustav Radbruch's theory of legal purpose is used as his analysis knife. The study concluded that closing the door of Isbat for Polygamous marriage is not the right solution because marriage isbat is one way to obtain legal guarantees in the eyes of the state. The aggrieved subject of the SEMA was a polygamous wife who could not take legal action in seeking justice. Judging from Gustav Radbruch's theory, SEMA number 3 of 2018 has not met the elements of legal objectives. The provisions in SEMA number 3 of 2018 only accommodate the interests of children. The rights of polygamous wives should be prioritized because the benefits received are more significant than tightly closing the door of isbat for Polygamous marriage. It is necessary to review SEMA number 3 of 2018 to contain concrete values of justice, expediency and legal certainty for children and wives.
Red Blood Profile Of Monopterus Albus Preserved In Multitesely Systems With Different Stock Densities Muhajir, Muhammad; Lukistyowati, Iesje; Syawal, Henni
Jurnal Akuakultur SEBATIN Vol. 4 No. 1 (2023): Mei
Publisher : Jurusan Budidaya Perairan, Fakultas Perikanan dan Kelautan, Universitas Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31258/jas.4.1.12-21

Abstract

Biofloc is a technology using good bacteria to convert organic waste to be food source by fish in the form of floc. This research was carried out in April-May 2021 in the Hatchery and blood observations at the Fish Disease and Parasite Laboratory, Faculty of Fisheries and Marine, University of Riau. The purpose of this study was to determine the health status of eels from the profile of erythrocytes cells and the best stocking density of eels cultivated in biofloc system. While the benefits of this study can be applied to biofloc cultivation and apply it in the field. The research method used one-factor completely randomized design (CRD) with four treatment levels and three replications (12 experimental units) for 40 days . The optimal stocking density of eels in clean water is 6 fish for 10 liters. The treatments in this study were P1: stocking density of 10 fish/25 L, P2: stocking density of 20 fish/25 L, P3: stocking density of 30 fish/25 L, P4: stocking density of 40 fish/25 L. The results showed that the erythrocytes profile of eel with different stocking densities had a significant effect (P<0.05) and the best treatment P3 (30 fish/25 L) with total erythrocytes 2.88x106 cells/mm3, hematocrit level 31.66 %, hemoglobin levels 17.40 g/dL, blood glucose 46.33 g/dL, specific growth rate 93.3%, and feed efficiency 67.46%. Water quality in this study was in normal range, that is temperature 25.7-27.3 oC, pH 7.0-7.8, DO 6.4-8.0 mg/L, and NH3 0.0003-0.00038 mg/L.
PRODAMAS chatbot: Aflask and support vector machine based implementation Mustain, Riefyal Arshyza; Muhajir, Muhammad; Ferdias, Pandri; Saputra, Nurirwan
Desimal: Jurnal Matematika Vol. 6 No. 2 (2023): Desimal: Jurnal Matematika
Publisher : Universitas Islam Negeri Raden Intan Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/djm.v6i2.17264

Abstract

In accelerated and equitable development in the Kediri City, the Kediri City Government launched the Community Empowerment Program called Prodamas. Prodamas aims to develop and encourage community participation in development at the Neighbourhood Level. To increase the dissemination of information about Prodamas, digital technology can be used as an information service provider. One of them is Chatbot. To develop Chatbots, Natural Language Processing, which is a branch of Artificial Intelligence, has become the most frequently used computer program. This Prodamas chatbot development uses the pattern matching method as an answer search algorithm and Support Vector Machine (SVM) classification as a method to see the machine's level of accuracy in answering questions given by users. Furthermore, the chatbot will be connected to WhatsApp so that it is expected to be able to provide and provide information about Prodamas. The results of testing the chatbot response with new questions provide an accuracy of 79%. Then testing the classification of the new question text with SVM. Obtained an accuracy of 88% with a precision value of 91% and a recall of 88%.
MODELLING EARTHQUAKE DISASTER DAMAGE DUE DEPTH OF EPICENTER AND MAGNITUDE USING SPATIAL REGRESSION Primananda, Dhea Laksmita Arsya; Muhajir, Muhammad
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 17 No 3 (2023): BAREKENG: Journal of Mathematics and Its Applications
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol17iss3pp1221-1234

Abstract

East Java Province is geographically close to the Eurasian and Indo-Australian Plate subduction zones, resulting in frequent earthquakes East Java Province has a high population density, so it is very risky if disaster occurs. One preventive solution to reduce this impact is estimating damage when an earthquake occurs. The purpose of this study was to determine the best modeling of damages due to earthquakes in East Java Province, using the amount of house damage as a response variable, while depth of the epicenter and the strength of the earthquake as predictor variables. It is suspected that there is a spatial dependency effect in this case, so the solution is to use regression with an area approach, namely the Spatial Durbin Model (SDM). The amount of house damage is collected from BNPB, the epicenter and the magnitude of earthquake collected from BMKG in 2021. The result shows that SDM is good at explaining the dependency relationship between response and predictor variables. The significant predictor variables are the depth of epicenter and the strength of the earthquake. It is meaning that the magnitude and the depth of the epicenter of the earthquake in an area have an impact on other adjacent areas. There is a relationship between the amount of house damage in one area and other adjacent areas. The Regency will have a high number of damaged houses if it is adjacent to a Regency that has a high number of damaged houses
SENTIMENT ANALYSIS OF OMNIBUS LAW USING SUPPORT VECTOR MACHINE (SVM) WITH LINEAR KERNEL Makhtum, Ahmad Rohiqim; Muhajir, Muhammad
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 17 No 4 (2023): BAREKENG: Journal of Mathematics and Its Applications
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol17iss4pp2197-2206

Abstract

The Omnibus Law is a recently enacted legislation that has been implemented within the regulatory framework of Indonesia. This legal framework, often denoted as the Universal Sweeping Law, consolidates multiple legal norms into a singular regulation. The Omnibus law encompasses a total of 11 distinct clusters, one of which pertains specifically to labor regulations. Nevertheless, the Omnibus law has elicited diverse reactions among the Indonesian populace, particularly on the Twitter platform. The researchers employed scraping techniques to extract tweets from Twitter users. A total of 3067 data points were collected during the period from March 20, 2022 to May 20, 2022. The data were subsequently categorized into positive, negative, and neutral sentiments. They were then assigned weights and classified using the Suport Vector Machine (SVM) method. The objective was to identify the public's sentiments towards the Omnibus law and evaluate the accuracy of the Support Vector Machine (SVM) method. The accuracy of the SVM algorithm with a linear kernel is found to be 97.05% based on its classification performance. There is a greater level of public concern and attention directed towards positive responses in relation to the Omnibus law, as opposed to negative responses. The positive responses encompassed the provision of favorable legislation to assist young entrepreneurs, whereas the negative responses pertained to concerns regarding persistently low wages for workers, despite the implementation of the Omnibus Law.
SEMA Waiver Number 3 of 2018 in the Case of Isbat for Polygamous Marriage: Study of Legal Considerations of Judges in Decision Number 634/Pdt.G/2018/PA.Mtr Muhajir, Muhammad; Uyun, Qurratul
Asy-Syir'ah: Jurnal Ilmu Syari'ah dan Hukum Vol 55 No 2 (2021)
Publisher : UIN Sunan Kalijaga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ajish.v55i2.1002

Abstract

Abstract: This article discusses the implementation of marriage isbat due to polygamy after the enactment of the Supreme Court Circular (SEMA) Number 3 of 2018. In the SEMA, the Supreme Court did not permit to ratify polygamous marriage isbat, but the decision of the Mataram Religious Court Number 634/Pdt.G /2018/PA.Mtr granted the application for polygamous marriage isbat. This paper aims to determine the decidendi ratio in the acceptance of the isbat of polygamous marriages. This research applies a statutory approach in a case. This study concludes that the Panel of Judges granted the case in decision Number 634 by ignoring SEMA Number 3 of 2018. Realizing justice and benefit for Siri's wife as heirs so that she can disburse her husband's pension TASPEN fund is seen as more beneficial by the Panel of Judges. In this way, her husband's pension TASPEN funds can be used to meet the living needs of the Petitioner and his family. The implication is that the decision can be called a legal breakthrough from the point of view of progressive law because it is based on the benefit that is considered more significant than following the material law of polygamous marriage. Abstrak: Artikel ini membahas pelaksanaan isbat nikah akibat poligami setelah berlakunya Surat Edaran Mahkamah Agung (SEMA) Nomor 3 Tahun 2018. Dalam SEMA Nomor 3 Tahun 2018, Mahkamah Agung tidak lagi memberikan izin untuk pengesahan isbat nikah poligami, namun putusan No.634/Pdt.G/2018/PA.Mtr mengabulkan permohonan isbat nikah poligami. Tujuan penulisan ini untuk mengetahui ratio decidendi dalam pengabulan isbat nikah poligami, apakah putusan catat hukum atau sebagai terobosan hukum. Penelitian ini merupakan kombinasi penelitian hukum normatif dan penelitian hukum empiris dengan pendekatan perundang-undangan (Statue Approach) dan pendekatan kasus (Case Approach). Penelitian dilakukan meliputi penelitian kepustakaan dan penelitian lapangan. Hasil penulisan ini adalah putusan perkara Nomor 634/Pdt.G/2018/PA.Mtr dikabulkan oleh Majelis Hakim dengan mengesampingkan SEMA Nomor 3 Tahun 2018. Putusan tersebut termasuk sebuah terobosan hukum dengan mencerminkan hukum progesif dengan mendasarkan kemaslahatan yang lebih utama ketimbang mengikuti hukum materiil yang mengatur tentang perkawinan poligami. Merealisasikan rasa keadilan dan kemaslahatan bagi isteri siri kedua sebagai ahli waris agar dapat mencairkan dana taspen pensiunan suami dipandang lebih maslahat oleh Majelis hakim. Sebab, dana taspen pensiunan suaminya tersebut dapat digunakan untuk mencukupi kebutuhan hidup Pemohon beserta keluarganya.
Integrating IndoBERT and balanced iterative reducing and clustering using hierarchies of BERTopic in Indonesian short text Muhajir, Muhammad; Gunardi, Gunardi; Danardono, Danardono; Rosadi, Dedi
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 5: October 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i5.pp4192-4201

Abstract

Short text topic modeling remains challenging due to data sparsity, limited word co-occurrences, and unstable clustering results, particularly for Indonesian texts. This study proposes an improved BERTopic framework that integrates IndoBERT embeddings, best match 25 (BM25)-based topic representation, and balanced iterative reducing and clustering using hierarchies (BIRCH) clustering to address these issues. IndoBERT generates contextual embeddings adapted to Indonesian linguistic features, and BM25 weighting improves keyword relevance by considering document length and term saturation. BIRCH clustering minimizes outliers by assigning most documents to valid clusters, which enhances data utilization and topic stability. Experiments on Indonesian datasets from X (formerly Twitter), Google Reviews, and YouTube demonstrate that the proposed approach consistently achieves higher topic coherence. The proposed method yields stable topic diversity values between 0.91 and 0.94, maintains embedding density from 0.60 to 0.66, and achieves intra-topic similarity between 0.39 and 0.41 across increasing dataset sizes. The proposed framework successfully reduces outlier proportions to 1-5%, which significantly outperforms standard BERTopic and K-Means. Furthermore, the model maintains stable topic counts as the data volume grows, confirming robustness and scalability for sparse short text modeling. Overall, integrating IndoBERT, BM25, and BIRCH provides a more coherent, stable, and effective solution for Indonesian short text topic modeling.