Amrullah Kamaruddin

@amru001@brin.go.id

Research Centre for Sustainable Production Systems and Life Cycle Assessment
Research Center for Appropriate Technology, Research Organization for Agriculture and Food National Research and Innovation Agency (BRIN)

Amrullah Kamaruddin


                  Download Compact PDF  
https://researchid.co/amrullah
My name is Amrullah Kamaruddin, born in Sinjai, South Sulawesi on 12 November 1973.I have worked for 16 years at BRIN in the energy and manufacturing research organisation as an implementer of sustainable production system research activities and life cycle assessment, Kelris smart & sustainable manufacturing system with a functional position of associate expert engineer.

EDUCATION

I graduated with a bachelor's degree in Electrical Engineering at UMI Makassar in 1999 and a master's degree in Informatics Engineering at Bina Nusantara University Jakarta in 2015 and a doctoral degree in Physics in the second semester at IPB

RESEARCH, TEACHING, or OTHER INTERESTS

Ecology, General Agricultural and Biological Sciences, Management Information Systems, Artificial Intelligence

FUTURE PROJECTS

Sistem Pengukuran Cepat Unsur Hara Tanah dengan Integrasi Near Infrared Spectroscopy

Soil nutrient management is a crucial aspect of smart and sustainable agriculture. However, challenges in rapid nutrient measurement and accurate data management often hamper the effectiveness of agricultural practices. These limitations lead to the need for technological solutions that can improve the reliability and security of nutrient measurement data, which ultimately affects productivity and environmental sustainability. The main objective of this research is to develop an optimal system for soil nutrient data measurement and management. The research methods include: system design integrating near infrared spectroscopy (NIRS) and blockchain, prototype development of the system design, and testing and validation of the prototype to evaluate system performance both in experimental and field situations. The practical implications of this research are the contribution to the development of smart and sustainable agriculture, as well as increasing agricultural productivity through more


Applications Invited
10

Scopus Publications

Scopus Publications

  • Prediction of Nitrogen Content in Wetland and Dryland Soils of Java Island Using Near-Infrared Spectroscopy and Multivariate Analysis
    Adnan Adnan, Yaya Suryana, Abdul Aziz, Taslim Rochmadi, Arie Rakhman Hakim, Fahrodji Fahrodji, Amrullah Kamaruddin, Wenny Oktaviani, Nizam Ghazali, Adim Hadi, Ardani Cesario Zuhri, Galang Ilman Islami
    Acta Technologica Agriculturae, 2026
    This study evaluated the potential of near-infrared spectroscopy (NIRS) combined with multivariate analysis to predict soil nitrogen (N) content in both wetland and dryland systems of Java Island, Indonesia. A total of 145 soil samples were collected across four provinces and analysed using a Frontier FT-NIR spectrometer in the 750–2500 nm range. Spectral data were pre-processed using several methods, and partial least squares regression (PLSR) models were calibrated and validated against reference Kjeldahl measurements. Among all approaches, asymmetric least-squares (ALS) baseline correction coupled with PLSR achieved the best predictive performance, with R ² = 0.882, RMSE = 0.0401% N, and RPD = 2.84 on the independent validation set. Characteristic wavelengths were identified around 1400, 1900, and 2200–2330 nm, corresponding to overtone and combination bands of N–H and O–H vibrations. The results confirm that NIRS offers a rapid, non-destructive, and cost-effective alternative for soil nitrogen assessment under diverse agroecosystems. This approach can support precision nutrient management in tropical smallholder farming systems and provides a foundation for developing portable, field-ready detection tools.
  • COMPARATIVE STUDY OF NIR-BASED MACHINE LEARNING FOR PREDICTING SOIL NUTRIENTS IN INDONESIAN FARMLANDS
    Adnan Adnan, Taufik Iqbal Ramdhani, Yaya Suryana, Abdul Aziz, Taslim Rochmadi, Amrullah Kamaruddin, Ninon Nurul Faiza
    Acta Technologica Agriculturae, 2026
    This study evaluates the efficacy of machine learning models for predicting soil nitrogen (N), phosphorus (P), and potassium (K) concentrations from near-infrared (NIR) spectral data (750–2499 nm). A comparative analysis was conducted on models from three distinct categories: linear-based, non-linear kernel-based, and neural network-based, using data from 145 soil samples collected across four Indonesian provinces. Regularised linear modelling performed best: Ridge Regression achieved R ²/MAE of 0.999/0.00005% for N-Total, 0.868/0.01408% for P-Total, and 0.763/0.01239% for K-Total. The non-linear SVR delivered moderate fit ( R ² = 0.821 for N-Total) but produced the lowest MAE for K (0.00829%) at lower explained variance ( R ² = 0.419). Neural network-based models underperformed the linear baselines. This study demonstrates that, for this dataset, a simpler regularised linear model outperformed more complex architectures, underscoring the critical role of rigorous model selection in developing accurate spectroscopic tools for precision agriculture. Future research could explore hybrid or ensemble methods to combine the strengths of different model types, potentially improving prediction accuracy and robustness.
  • The effect of ionic radius carbon dot on Ti4+ in lattice parameters of Ba0.2Sr0.8TiO3 thin films
    Ahmad Ripai, Aep Setiawan, W.D. Laksanawati, Amrullah Kamaruddin, Noviyan Darmawan, Johan Iskandar, Irzaman
    Bio Web of Conferences, 2025
    Barium Strontium Titanate (Ba₀.₂Sr₀.₈TiO₃) thin films doped with carbon dots at varying concentrations (0%, 2%, 4%, and 6%) were successfully synthesized using the Chemical Solution Deposition (CSD) method. The films were deposited on p-type (100) silicon substrates via spin coating at 8000 rpm, followed by annealing at 850 °C for 8 hours. Structural characterization using X-ray Diffraction (XRD) confirmed a cubic lattice structure for all samples, with lattice parameters (a = b = c) measured as 3.306 Å, 3.324 Å, 3.336 Å, and 3.311 Å for the 0%, 2%, 4%, and 6% doping levels. The observed increase in lattice parameters with higher carbon dot concentrations is attributed to the larger ionic radius of carbon dots (10 Å) compared to Ti⁴⁺ (0.61 Å). These results indicate that carbon dot incorporation modulates the structural properties of Ba₀.₂Sr₀.₈TiO₃ films, which could have significant implications for their functional applications.
  • A bibliometric review of the effects of carbon pollution on soil nutrient quality in sustainable agriculture: exploring future research directions
    Amrullah Kamaruddin, Agus Kartono, Rony Febryarto, Adnan Adnan, Syaeful Karim
    Journal of Physics Conference Series, 2025
    Sustainable agriculture is a system that aims to meet food needs while ensuring environmental health and social equity in the long term. One of the main challenges in sustainable agriculture is carbon pollution which can damage the nutritional quality of the soil. Carbon pollution from industrial, agricultural, transportation, and deforestation significantly affects soil quality globally. The concentration of carbon dioxide in the atmosphere and global warming can readily arise, leading to a decline in soil functionality and organic carbon levels within the soil. This issue is addressed through a bibliometric research approach to examine scientific publications on the effects of carbon emissions on soil nutrient quality within the framework of sustainable agriculture. The study aims to generate future insights and supply essential information for designing effective research methodologies and agricultural practices to mitigate the effects of carbon emissions on soil quality while advancing sustainable farming practices. The results of research studies conducted between 2020 and 2024, using geographical analysis, show that most of the contributions of studies in this field come from China, Spain, Italy, and India.
  • Performance improvement of an automatic airbag-based mechanical ventilator: Engineering experiences during Covid-19 pandemic
    Pratondo Busono, Riky Alam Ma’arif, Dede Sumantri, I. Putu Ananta Yogiswara, Rony Febryanto, Syaeful Karim, Riyanto Riyanto, Marlin A. Baidillah, I. Made Astawa, Amrullah Kamaruddin, Arief Barkah, Dimas Sangaji, Arky Astasari
    Aip Conference Proceedings, 2024
  • Enhancing Maize Germplasm Selection for Genebanks: A Decision Support System Combining Shannon-Weaver Diversity Index and Machine Learning
    Adnan Adnan, Yaya Suryana, Abdul Aziz, Taslim Rochmadi, Arie Rakhman Hakim, Andari Risliawati, Arifuddin Kasim, Fahrodji Fahrodji, Amrullah Kamaruddin, Wenny Oktaviani, Laela Nuraini, Anugerah Fitri Amalia, Nizam Ghazali, Adim Hadi, Taufik Iqbal Ramdhani, Puji Lestari, Willy Bayuardi Suwarno, Trikosoemaningtyas Trikosoemaningtyas, Sobir Sobir
    International Journal of Design and Nature and Ecodynamics, 2024
    While core collections offer various advantages, achieving a balance between representing genetic diversity and ensuring the practical manageability of the entire genebank collection is crucial.This study investigated the utility of the Shannon-Weaver diversity index and machine learning as a support system for the acceptability of new maize accessions into the genebank collection.This study examined 1279 maize germplasm accessions from the Agricultural Genebank Indonesia.The maize germplasm collection was divided into two parts.The first part, namely subset A, contains 600 accessions, which acted as original collections and were randomly selected for calculating the diversity values in each kernel character using the Shannon-Weaver diversity index.The second part, subset B, consisting of 679 accessions, was used to determine whether each accession was similar or different from subset A using an Excel macro-based application built by the authors.Principal component analysis (PCA) and Mahalanobis distances were used in the first step to identify outliers in data points with nine independent variables, namely kernel type, kernel color, presence of white cap, mottled type, kernel upper surface shape, kernel weight, kernel length, width, and thickness.Seventeen outlier samples, detected through PCA and Mahalanobis distances, were intentionally excluded from the dataset to ensure the integrity of subsequent machine learning analyses.The subset B was then divided into two parts to perform conventional and novel machine learning, i.e., linear discriminant analysis (LDA) and Tabnet.The results of this study show that the model's accuracy of LDA and TabNet were 89.36% and 86.4%, respectively.By integrating the Shannon-Weaver diversity index and machine learning methodologies, this research offers a comprehensive decision support system for guiding the acceptance of new maize accessions.The proposed system implies optimizing genebank strategies for the integrity and adaptability of maize germplasm collections.
  • Predictive soil nutrient modeling with spectral data and machine learning in four major Indonesian Provinces located on the island of java
    T I Ramdhani, Adnan, Y Suryana, T Rochmadi, A Aziz, A Kamaruddin, N Ghazali, A Hadi, W Oktaviani, S V Budiwati, A R Hakim, Fahrodji, L Nuraini
    Iop Conference Series Earth and Environmental Science, 2024
    This study provides a detailed analysis of predicting soil nutrient content using spectral data and machine learning techniques in four Indonesian provinces: West Java, Central Java, Yogyakarta (DIY), and East Java. The research collected 145 soil samples to predict various key soil nutrients, such as N Total, NH4, NO3, P Total, P Available, K Total, K Available, C Organic, and pH. The study used linear regression (LR) and deep neural networks (DNN) with a deep cross-network (DCN) architecture to model the relationships between soil spectral data and nutrient content. LR was used as a baseline model to understand linear relationships between spectral features and soil properties and identify the most influential spectral frequencies in predicting soil nutrient levels. On the other hand, the DNN model captured complex, non-linear patterns within the data. Results showed that while the DNN model displayed advanced capabilities, the LR model generally outperformed it in predictive accuracy, particularly for nutrients like N-Total, P-Total, and K-Total. The findings highlight the potential of combining spectral data with advanced machine-learning techniques for precise soil nutrient estimation, which could significantly enhance agricultural productivity and soil management practices in Indonesia.
  • Development of mobile biosensor reader for wearable sweat glucose biosensor application
    P Busono, R Febryarto, R A Ma’arif, I M Astawa, I P A Yogiswara, S Karim, F A Majid, A Amrullah, S Rahayu, M Rahmah
    Journal of Physics Conference Series, 2023
    Sweat contains numerous biomarkers, including glucose, which can provide valuable insights into an individual’s metabolic state. Noninvasive glucose monitoring eliminates the need for frequent finger pricks or blood samples, offering greater convenience and reducing discomfort for individuals with diabetes. These biosensors are designed to detect and quantify glucose levels through various sensing mechanisms, such as enzymatic reactions or electrochemical measurements. The integration of biosensors into wearable devices, such as smartwatches, patches, or flexible electronics, allows for mobile glucose monitoring in sweat. Accurate glucose measurements require calibration and validation against reference measurements, such as blood glucose levels. Research focuses on developing calibration algorithms and improving the accuracy and reliability of mobile glucose biosensors in sweat.
  • Heart Sound Signal Analysis for Digital Auscultation
    P Busono, S Karim, A Kamaruddin, I P A Yogiswara
    Journal of Physics Conference Series, 2022
    Cardiac auscultation is the examination of the heart by listening to the sound produced by the heart through a stethoscope. Heart sounds can provide information about the functioning of the heart valve condition as well as information about the structural abnormalities of the heart. However, it needs intensive training for mastering. The objective of the work was to develop an algorithm for heart sound signal classification applied to computer-assisted digital auscultation in order to identify pathological events. The method can be described as follow: data collection, pre-processing, segmentation, feature extraction, and classification. The data were collected from volunteers using an electronic stethoscope and from a database available in the internet. The heart sound data were then extracted and split into training, validation, and testing datasets. In the training process the dataset was labeled as normal and abnormal (aortic stenosis, mitral stenosis, aortic regurgitation, pulmonic regurgitation, tricuspid stenosis, flow murmur, and patent ductus arteriosus). The convolution neural network is used as a classifier in the learning process to obtain the learning model. The model was validated and tested using the available datasets. The experimental results show that the algorithm has the capability to classify the heart sound into normal and abnormal with a high detection rate.
  • Effectiveness of model numbered head type integrated structure of islamic value against understanding mathematical concept ability
    F Febryanti, H Ahmad, Nurhasanah, A Kamaruddin
    Journal of Physics Conference Series, 2020
    To realize the mandate of law number 20 of 2003, the teacher can integrate Islam value in mathematics learning. This study is a quasi-experimental study that aims to determine the effectiveness of the application of cooperative learning models with numbered structure types that are integrated Islamic values with the ability to understand students’ mathematical concepts. The sample of this research is the class X students of SMK Mega Link Majene, amounting to 20 people. Indicators of effectiveness in this study include (1) the value of student learning attain Minimum Completion Criteria (KKM = 70) with 80% classical completeness, (2) observation sheet for student activities in each observed aspect reaching > 75%, and (3) the questionnaire response to the application of cooperative learning models with integrated structure numbered head type Islamic values reached > 75% who responded positively. The analysis results obtained a significant value of 0, 000 < α means that H0 is rejected and accepts H1. While the classical completeness value got 85% of students who achieved KKM, the observation sheet of student activities reached 85% of the eight observed aspects and calculated the students’ responses to the application of learning data 88% responded positively. Based on this analysis, the use of cooperative learning models with head types with structural numbers integrated with effective Islamic values on the ability to understand students’ mathematical concepts.