Aji Ery Burhandenny
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Aji Ery Burhandenny has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Didit Suprihanto
Universitas Mulawarman
5 shared publications - Hirohisa Aman
Ehime University
5 shared publications - Happy Nugroho
Universitas Mulawarman
4 shared publications Minoru Kawahara
4 shared publications- Restu Mukti Utomo
Program Studi Teknik Elektro, Universitas Mulawarman
3 shared publications Adi Pandu Wirawan
2 shared publications
Latest Publications
- Open Access
- 17 January 2026
- Published by Universitas Malikussaleh in International Journal of Engineering, Science and Information Technology
- Vol. 6 (1) , 36-43
Improving TDS Sensor Accuracy in an IoT-Based Fertigation Prototype Using Polynomial Regression Calibration and Interpolation
Accurate measurement of Total Dissolved Solids (TDS) is a critical requirement for hydroponic nutrient management, especially in automated fertigation systems that adjust nutrient concentrations based on plant age. However, non-industrial TDS sensors often exhibit significant fluctuations and non-linear errors, leading to unreliable nutrient dosing. This study proposes a calibration approach using second-order polynomial regression combined with interpolation to improve the accuracy of TDS measurements in an IoT-based fertigation prototype for lettuce hydroponics. The calibration was performed using reference TDS solutions and a digital TDS meter to ensure accurate measurements. The results show that the Mean Absolute Percentage Error (MAPE) decreased from 24.771% to 7.5768% during calibration, demonstrating a significant improvement in measurement accuracy. The calibrated sensor readings fall within the acceptable range for hydroponic nutrient control (±10%). This method provides a low-cost, reliable alternative for improving sensor accuracy in IoT fertigation systems.
- 17 January 2026
- Published by Universitas Malikussaleh in International Journal of Engineering, Science and Information Technology
- Vol. 6 (1) , 36-43
Open AccessImproving TDS Sensor Accuracy in an IoT-Based Fertigation Prototype Using Polynomial Regression Calibration and Interpolation
Accurate measurement of Total Dissolved Solids (TDS) is a critical requirement for hydroponic nutrient management, especially in automated fertigation systems that adjust nutrient concentrations based on plant age. However, non-industrial TDS sensors often exhibit significant fluctuations and non-linear errors, leading to unreliable nutrient dosing. This study proposes a calibration approach using second-order polynomial regression combined with interpolation to improve the accuracy of TDS measurements in an IoT-based fertigation prototype for lettuce hydroponics. The calibration was performed using reference TDS solutions and a digital TDS meter to ensure accurate measurements. The results show that the Mean Absolute Percentage Error (MAPE) decreased from 24.771% to 7.5768% during calibration, demonstrating a significant improvement in measurement accuracy. The calibrated sensor readings fall within the acceptable range for hydroponic nutrient control (±10%). This method provides a low-cost, reliable alternative for improving sensor accuracy in IoT fertigation systems.
- Open Access
- 1 August 2025
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 14 (4) , 3006-3014
A comparative study of machine learning methods for drug type classification
Drugs, commonly called narcotics, are dangerous substances that, if consumed excessively, can result in addiction and even death. Drug abuse in Indonesia has reached a concerning stage. In 2017, the National Narcotics Agency detected 46,537 drug-related incidents, including methamphetamine, marijuana, and ecstasy. There are 4 types of substances that can affect drug users, such as hallucinogens, depressants, opioids, and stimulants. A machine learning approach can detect these substances using user symptom data as input. This study uses six different methods in classifying, including decision tree, C.45, K-nearest neighbor (KNN), random forest, and support vector machine (SVM). The dataset comprises 144 data and 21 attributes based on the user's symptoms. The evaluation method in this study uses cross-validation with K-fold values of 5 and 10 and uses three parameters: precision, recall, and accuracy. KNN yields the most optimal results by using K=1 and K-fold 10 in the Euclidean and Minkowski types. The model achieves precision, recall, and accuracy of 91.9%, 91.7%, and 91.67%, respectively.
- 1 August 2025
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 14 (4) , 3006-3014
Open AccessA comparative study of machine learning methods for drug type classification
Drugs, commonly called narcotics, are dangerous substances that, if consumed excessively, can result in addiction and even death. Drug abuse in Indonesia has reached a concerning stage. In 2017, the National Narcotics Agency detected 46,537 drug-related incidents, including methamphetamine, marijuana, and ecstasy. There are 4 types of substances that can affect drug users, such as hallucinogens, depressants, opioids, and stimulants. A machine learning approach can detect these substances using user symptom data as input. This study uses six different methods in classifying, including decision tree, C.45, K-nearest neighbor (KNN), random forest, and support vector machine (SVM). The dataset comprises 144 data and 21 attributes based on the user's symptoms. The evaluation method in this study uses cross-validation with K-fold values of 5 and 10 and uses three parameters: precision, recall, and accuracy. KNN yields the most optimal results by using K=1 and K-fold 10 in the Euclidean and Minkowski types. The model achieves precision, recall, and accuracy of 91.9%, 91.7%, and 91.67%, respectively.
- Open Access
- 6 June 2025
- Published by Atlantis Press SARL
- p. 476-488
Evaluation Study of 150 kV Current Transformer at Bayline 1 Kota Bangun Bukit Biru Substation
- 6 June 2025
- Published by Atlantis Press SARL
- p. 476-488
Open AccessEvaluation Study of 150 kV Current Transformer at Bayline 1 Kota Bangun Bukit Biru Substation
- Open Access
- 6 June 2025
- Published by Atlantis Press SARL
- p. 108-126
Automatic Temperature, Lighting, and Fish Feeder Control and Monitoring Systems in Aquascape based on the Internet of Things
- 6 June 2025
- Published by Atlantis Press SARL
- p. 108-126
Open AccessAutomatic Temperature, Lighting, and Fish Feeder Control and Monitoring Systems in Aquascape based on the Internet of Things
- Open Access
- 6 June 2025
- Published by Atlantis Press SARL
- p. 257-274
Communication Performance Test of LoRa-Based Vibration Monitoring System
- 6 June 2025
- Published by Atlantis Press SARL
- p. 257-274
Open AccessCommunication Performance Test of LoRa-Based Vibration Monitoring System
- Open Access
- 1 December 2024
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 13 (4) , 4241-4248
Image analysis for classifying coffee bean quality using a multi feature and machine learning approach
Price and customer satisfaction depend on coffee bean quality. The coffee industry must analyze coffee bean quality. Global demand for robusta coffee is high. Coffee industry professionals mostly understand coffee bean quality. Thus, an image analysis using a computer vision-based approach for classifying robusta coffee bean quality is required. Image acquisition, region of interest (ROI) detection, pre-processing, segmentation, feature extraction, feature selection, and classification are covered in this study. A multi-feature derived based on color, shape, and texture features was employed in feature extraction, followed by feature selection using principal component analysis (PCA). Several machine-learning methods classified the coffee beans. The method performance was assessed using precision, recall, and accuracy. The selected features using the backpropagation neural network (BPNN) classifier outperformed others with 98.54% accuracy.
- 1 December 2024
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 13 (4) , 4241-4248
Open AccessImage analysis for classifying coffee bean quality using a multi feature and machine learning approach
Price and customer satisfaction depend on coffee bean quality. The coffee industry must analyze coffee bean quality. Global demand for robusta coffee is high. Coffee industry professionals mostly understand coffee bean quality. Thus, an image analysis using a computer vision-based approach for classifying robusta coffee bean quality is required. Image acquisition, region of interest (ROI) detection, pre-processing, segmentation, feature extraction, feature selection, and classification are covered in this study. A multi-feature derived based on color, shape, and texture features was employed in feature extraction, followed by feature selection using principal component analysis (PCA). Several machine-learning methods classified the coffee beans. The method performance was assessed using precision, recall, and accuracy. The selected features using the backpropagation neural network (BPNN) classifier outperformed others with 98.54% accuracy.
- Open Access
- 24 July 2024
- Published by Infinite Corporation in Jurnal Teknik Informatika (Jutif)
- Vol. 5 (4) , 1035-1042
COMPARISON OF SUPPORT VECTOR MACHINE AND INDOBERT IN NON-FUNCTIONAL REQUIREMENT CLASSIFICATION OF APPLICATION USER REVIEWS
User reviews of mobile applications have become a valuable source of information for evaluating the quality of an application. It is crucial for application developers to understand what users express in their reviews. One aspect that can be analyzed from user reviews is Non-Functional Requirement (NFR). Classifying reviews based on NFR is essential in understanding how an application can be enhanced. Although user reviews have the potential to provide valuable insights into NFR, manually processing thousands of user reviews is a laborious and inefficient task. Therefore, artificial intelligence methods are employed to automatically classify user reviews into relevant NFR categories. This research discusses the performance comparison of the SVM and IndoBERT algorithms in NFR classification. The study involves collecting application review data from 2018 to 2023, sourced from Google Playstore and Apple Appstore, followed by annotating the review data based on ISO 25010. Subsequently, the data is allocated into training and testing sets with an 80:20 ratio. Further, a data preprocessing phase is conducted, which includes steps such as lowercasing, tokenization, special character removal, text normalization, and text stemming. The next step involves training the SVM and IndoBERT algorithms on the dataset. Finally, the evaluation is carried out by calculating the F1-score. The research results indicate that the IndoBERT model outperforms the SVM model. The IndoBERT algorithm excels in recognizing NFR in reviews, achieving an F1-score of 93%, while the SVM algorithm achieves an F1-score of 91%.
- 24 July 2024
- Published by Infinite Corporation in Jurnal Teknik Informatika (Jutif)
- Vol. 5 (4) , 1035-1042
Open AccessCOMPARISON OF SUPPORT VECTOR MACHINE AND INDOBERT IN NON-FUNCTIONAL REQUIREMENT CLASSIFICATION OF APPLICATION USER REVIEWS
User reviews of mobile applications have become a valuable source of information for evaluating the quality of an application. It is crucial for application developers to understand what users express in their reviews. One aspect that can be analyzed from user reviews is Non-Functional Requirement (NFR). Classifying reviews based on NFR is essential in understanding how an application can be enhanced. Although user reviews have the potential to provide valuable insights into NFR, manually processing thousands of user reviews is a laborious and inefficient task. Therefore, artificial intelligence methods are employed to automatically classify user reviews into relevant NFR categories. This research discusses the performance comparison of the SVM and IndoBERT algorithms in NFR classification. The study involves collecting application review data from 2018 to 2023, sourced from Google Playstore and Apple Appstore, followed by annotating the review data based on ISO 25010. Subsequently, the data is allocated into training and testing sets with an 80:20 ratio. Further, a data preprocessing phase is conducted, which includes steps such as lowercasing, tokenization, special character removal, text normalization, and text stemming. The next step involves training the SVM and IndoBERT algorithms on the dataset. Finally, the evaluation is carried out by calculating the F1-score. The research results indicate that the IndoBERT model outperforms the SVM model. The IndoBERT algorithm excels in recognizing NFR in reviews, achieving an F1-score of 93%, while the SVM algorithm achieves an F1-score of 91%.
- Open Access
- 16 August 2023
- Published by Universitas Muslim Indonesia in ILKOM Jurnal Ilmiah
- Vol. 15 (2) , 303-316
Design and Build of IoT Based Flood Prone Monitoring System at Semani’s Pump House Drainage System
Floods are a common disaster in watersheds, and flood control is difficult. However, losses can be reduced by quickly disseminating alert status information. This paper proposes a prototype of a monitoring system that can determine the status of flood alerts in real time and quickly disseminating to the community, allowing people to be better prepared for flood disasters. The system was developed using the R&D method and consists of hardware and software development. The hardware comprises several sensor modules to read the discharge, temperature, humidity, and water level and to transmit the readings to the software. The software is divided into two applications: a website application and a Telegram application. The public can find the flood alert status history data from the website and obtain flood alert status warning messages and the latest alert status from Telegram. The results of the tests indicated that the sensors were very accurate, with a MAPE value of less than 10%. The software test also showed that the input and output were according to design. The proposed system can potentially reduce flood losses by providing early warning information to the community. The system is also scalable and adaptable to other watersheds.
- 16 August 2023
- Published by Universitas Muslim Indonesia in ILKOM Jurnal Ilmiah
- Vol. 15 (2) , 303-316
Open AccessDesign and Build of IoT Based Flood Prone Monitoring System at Semani’s Pump House Drainage System
Floods are a common disaster in watersheds, and flood control is difficult. However, losses can be reduced by quickly disseminating alert status information. This paper proposes a prototype of a monitoring system that can determine the status of flood alerts in real time and quickly disseminating to the community, allowing people to be better prepared for flood disasters. The system was developed using the R&D method and consists of hardware and software development. The hardware comprises several sensor modules to read the discharge, temperature, humidity, and water level and to transmit the readings to the software. The software is divided into two applications: a website application and a Telegram application. The public can find the flood alert status history data from the website and obtain flood alert status warning messages and the latest alert status from Telegram. The results of the tests indicated that the sensors were very accurate, with a MAPE value of less than 10%. The software test also showed that the input and output were according to design. The proposed system can potentially reduce flood losses by providing early warning information to the community. The system is also scalable and adaptable to other watersheds.
- Open Access
- 30 June 2023
- Published by STMIK Dharma Wacana in International Journal of Artificial Intelligence Research
- Vol. 7 (1) , 1-9
An extraction of shapes and support vector machine methods for identification of decorative wall “Lamin” motifs of the Dayak Kenyah Pampang tribe
One of the Dayak cultures of Kalimantan Island, Indonesia is a traditional house called Lamin where each wall is decorated according to tribal characteristics. This study aims to identify the image on the Lamin wall using the Support Vector Machine (SVM) method based on the eccentricity and metric parameter values. The data of this study consisted of 50 types of images of the Lamin wall motifs of the Dayak Kenyah tribe consisting of tebengaang, dragon, crocodile, tiger, and arch which were taken from the tourist village, Pampang, Samarinda, East Kalimantan. Based on the experiment, the shape feature extraction method has produced the highest value of the eccentricity parameter which is 0.6979 and the metric parameter is 0.9953 on the image of the arch. Motif identification using the SVM method using linear, Gaussian/RBF, and polynomial kernel parameters has resulted in the highest accuracy with 80% image composition of kernel polynomial at 85%, Gaussian/RBF at 80%, and linear at 78%.
- 30 June 2023
- Published by STMIK Dharma Wacana in International Journal of Artificial Intelligence Research
- Vol. 7 (1) , 1-9
Open AccessAn extraction of shapes and support vector machine methods for identification of decorative wall “Lamin” motifs of the Dayak Kenyah Pampang tribe
One of the Dayak cultures of Kalimantan Island, Indonesia is a traditional house called Lamin where each wall is decorated according to tribal characteristics. This study aims to identify the image on the Lamin wall using the Support Vector Machine (SVM) method based on the eccentricity and metric parameter values. The data of this study consisted of 50 types of images of the Lamin wall motifs of the Dayak Kenyah tribe consisting of tebengaang, dragon, crocodile, tiger, and arch which were taken from the tourist village, Pampang, Samarinda, East Kalimantan. Based on the experiment, the shape feature extraction method has produced the highest value of the eccentricity parameter which is 0.6979 and the metric parameter is 0.9953 on the image of the arch. Motif identification using the SVM method using linear, Gaussian/RBF, and polynomial kernel parameters has resulted in the highest accuracy with 80% image composition of kernel polynomial at 85%, Gaussian/RBF at 80%, and linear at 78%.
- Open Access
- 6 December 2022
- Published by International Association of Online Engineering (IAOE) in International Journal of Online and Biomedical Engineering (iJOE)
- Vol. 18 (15) , 202-215
Naïve Bayes and K-Nearest Neighbor Algorithms Performance Comparison in Diabetes Mellitus Early Diagnosis
Diabetes Mellitus (DM) is a chronic disease that occurs when the body cannot effectively use the insulin it produces. The use of artificial intelligence (AI) can provide a means to diagnose. This study aims to obtain the best classification of the Naïve Bayes (NB) and K-Nearest Neighbors (KNN) methods so that accurate results are obtained in diagnosing DM disease using a dataset originating from The Abdul Moeis Hospital, Samarinda, East Kalimantan, Indonesia. The results showed that the KNN performed better in accuracy, precision, and specificity with an Area Under the Curve (AUC) value 10% higher than NB. Overall, KNN obtained a better recall compared to the NB in order to DM diagnosis.
- 6 December 2022
- Published by International Association of Online Engineering (IAOE) in International Journal of Online and Biomedical Engineering (iJOE)
- Vol. 18 (15) , 202-215
Open AccessNaïve Bayes and K-Nearest Neighbor Algorithms Performance Comparison in Diabetes Mellitus Early Diagnosis
Diabetes Mellitus (DM) is a chronic disease that occurs when the body cannot effectively use the insulin it produces. The use of artificial intelligence (AI) can provide a means to diagnose. This study aims to obtain the best classification of the Naïve Bayes (NB) and K-Nearest Neighbors (KNN) methods so that accurate results are obtained in diagnosing DM disease using a dataset originating from The Abdul Moeis Hospital, Samarinda, East Kalimantan, Indonesia. The results showed that the KNN performed better in accuracy, precision, and specificity with an Area Under the Curve (AUC) value 10% higher than NB. Overall, KNN obtained a better recall compared to the NB in order to DM diagnosis.