Didit Suprihanto
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Didit Suprihanto has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Aji Ery Burhandenny
Mulawarman University
5 shared publications - Happy Nugroho
Universitas Mulawarman
3 shared publications Adi Pandu Wirawan
2 shared publications- Anindita Septiarini
Universitas Mulawarman
2 shared publications - Budi Yannur
Program Studi Teknik Elektro, Universitas Mulawarman
2 shared publications - Restu Mukti Utomo
Program Studi Teknik Elektro, Universitas Mulawarman
2 shared publications
Latest Publications
- Open Access
- 1 October 2025
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 14 (5) , 3692-3703
Comparative performance analysis of LSTM, GRU, and bidirectional neural networks for political ideology classification
Political ideology classification is crucial for understanding social polarization, monitoring democratic processes, and identifying bias on online platforms. This study compares the performance of long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional GRU (Bi-GRU) neural network models in classifying liberal and conservative political ideologies from social media text data. The Bi-GRU achieved the best results with 88.75% accuracy and 89.16% F1-score, highlighting its strength in contextual analysis. These findings suggest their applicability in areas such as election monitoring and the analysis of political discourse. This study contributes to the field of political text classification by offering a comparative analysis of deep learning architectures. The dataset utilized covers a wide range of issues, including social, political, economic, religious, and racial topics, demonstrating its comprehensive nature. Visualizations using WordCloud and uniform manifold approximation and projection (UMAP) reveal distinct ideological patterns, validating the dataset’s quality for training models. The findings underscore the importance of utilizing advanced bidirectional architectures for nuanced tasks, such as ideology classification, where contextual understanding is crucial. These insights open avenues for future research, such as the application of Bi-GRU in analyzing multilingual political ideologies or real-time sentiment tracking during election campaigns.
- 1 October 2025
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 14 (5) , 3692-3703
Open AccessComparative performance analysis of LSTM, GRU, and bidirectional neural networks for political ideology classification
Political ideology classification is crucial for understanding social polarization, monitoring democratic processes, and identifying bias on online platforms. This study compares the performance of long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional GRU (Bi-GRU) neural network models in classifying liberal and conservative political ideologies from social media text data. The Bi-GRU achieved the best results with 88.75% accuracy and 89.16% F1-score, highlighting its strength in contextual analysis. These findings suggest their applicability in areas such as election monitoring and the analysis of political discourse. This study contributes to the field of political text classification by offering a comparative analysis of deep learning architectures. The dataset utilized covers a wide range of issues, including social, political, economic, religious, and racial topics, demonstrating its comprehensive nature. Visualizations using WordCloud and uniform manifold approximation and projection (UMAP) reveal distinct ideological patterns, validating the dataset’s quality for training models. The findings underscore the importance of utilizing advanced bidirectional architectures for nuanced tasks, such as ideology classification, where contextual understanding is crucial. These insights open avenues for future research, such as the application of Bi-GRU in analyzing multilingual political ideologies or real-time sentiment tracking during election campaigns.
- 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. 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
- 30 May 2025
- Published by Universitas Islam Indonesia (Islamic University of Indonesia) in AJIE
- p. 84-95
Optimal Scheduling of IoT Devices Using Round Robin Algorithm in Environmental Monitoring Systems: A Simulation Approach
This study explores the application of the Round Robin algorithm for scheduling tasks in Internet of Things (IoT) systems designed for environmental monitoring, such as temperature and humidity tracking. Efficient task scheduling is critical to minimize latency and energy consumption in IoT networks. Using a Python-based simulation, this research evaluates the performance of the Round Robin algorithm in managing 10 to 50 virtual IoT devices tasked with environmental data collection, comparing it with Priority with Aging and Genetic Algorithm approaches. The simulation results indicate that Round Robin reduces the average waiting time by 15% compared to random scheduling, while the Genetic Algorithm outperforms Round Robin by approximately 20% in high-density networks. This approach provides valuable insights into IoT scheduling efficiency without requiring physical deployment, making it relevant for large-scale IoT system development.
- 30 May 2025
- Published by Universitas Islam Indonesia (Islamic University of Indonesia) in AJIE
- p. 84-95
Open AccessOptimal Scheduling of IoT Devices Using Round Robin Algorithm in Environmental Monitoring Systems: A Simulation Approach
This study explores the application of the Round Robin algorithm for scheduling tasks in Internet of Things (IoT) systems designed for environmental monitoring, such as temperature and humidity tracking. Efficient task scheduling is critical to minimize latency and energy consumption in IoT networks. Using a Python-based simulation, this research evaluates the performance of the Round Robin algorithm in managing 10 to 50 virtual IoT devices tasked with environmental data collection, comparing it with Priority with Aging and Genetic Algorithm approaches. The simulation results indicate that Round Robin reduces the average waiting time by 15% compared to random scheduling, while the Genetic Algorithm outperforms Round Robin by approximately 20% in high-density networks. This approach provides valuable insights into IoT scheduling efficiency without requiring physical deployment, making it relevant for large-scale IoT system development.
- Open Access
- 1 September 2024
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 13 (3) , 2656-2665
Recommendation method for selecting the rice seeds based on group decision support system
In this paper, we provide group recommendations based on each decision makers (DMs) in choosing the best type of rice for replanting. This group decision support system (GDSS) aims to guide stakeholders who have a role in selecting rice types. In this method, we propose using technique for order preference by similarity to ideal solution (TOPSIS) to rank each DM, Borda to rank in groups, and then test it using Spearman's rank correlation to measure the relationship between system results and the method applied. The results of this study show that DM1 ranks highest in selecting Gelagai rice seeds with a preference of 0.7786. Then DM2 ranked highest with Ekor Payau rice seeds in preference 0.6529. Meanwhile, DM3 ranked highest in Gelagai rice seeds with a selection of 0.7728. The final group voting system uses Borda, where Gelagai rice seeds occupy the highest rank with the most accumulated votes from each DMs. The best option or the highest rating based on the assessment of the three DMs, DM1 as a farmer is the first rank A10 Gelagai with a score of Borda 26 in the decision group selection of superior rice seeds.
- 1 September 2024
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 13 (3) , 2656-2665
Open AccessRecommendation method for selecting the rice seeds based on group decision support system
In this paper, we provide group recommendations based on each decision makers (DMs) in choosing the best type of rice for replanting. This group decision support system (GDSS) aims to guide stakeholders who have a role in selecting rice types. In this method, we propose using technique for order preference by similarity to ideal solution (TOPSIS) to rank each DM, Borda to rank in groups, and then test it using Spearman's rank correlation to measure the relationship between system results and the method applied. The results of this study show that DM1 ranks highest in selecting Gelagai rice seeds with a preference of 0.7786. Then DM2 ranked highest with Ekor Payau rice seeds in preference 0.6529. Meanwhile, DM3 ranked highest in Gelagai rice seeds with a selection of 0.7728. The final group voting system uses Borda, where Gelagai rice seeds occupy the highest rank with the most accumulated votes from each DMs. The best option or the highest rating based on the assessment of the three DMs, DM1 as a farmer is the first rank A10 Gelagai with a score of Borda 26 in the decision group selection of superior rice seeds.
- Open Access
- 20 June 2022
- Published by State University of Medan in CESS (Journal of Computer Engineering, System and Science)
- Vol. 7 (2) , 537-546
Drugs Consumption Clustering Model using K-Means Technique
Persediaan obat pada suatu Puskesmas seringkali habis sebelum jadwal penerimaan obat dilakukan hal ini dikarenakan Kejadian Luar Biasa (KLB). Sehingga, perencanaan persediaan obat yang efektif dan efisien dengan menerapkan metode kecerdasan buatan dalam rangka membantu pihak manajemen sangat diperlukan. Penelitian ini bertujuan untuk memonitoring persediaan obat sebagai salah satu dasar dalam permintaan obat. Data pemakaian obat yang digunakan berasal dari Laporan Pemakaian dan Lembar Permintaan Obat (LPLPO) UPTD Puskesmas Lempake tahun 2016-2018 dan telah dinormalisasi dengan metode Z-Score. Metode K-Means telah diterapkan sebanyak 3 cluster terdiri tinggi (C1), sedang (C2) dan kurang (C3) dimana penentuan titik centroid berdasarkan nilai max, average, dan min. Sedangkan, metode jarak Euclidean distance telah ditetapkan untuk menganalisis jarak data tiap cluster. Hasil temuan mengindikasikan bahwa pengujian cluster menggunakan Sum of Squared Error (SSE) telah mendapatkan nilai sebesar 77,34814. Dimana, hasil pengelompokkan yaitu C1 sebanyak 5 data, C2 sebanyak 14 data, dan C3 sebanyak 206 data. Hal ini berarti bahwa 3 cluster merupakan hasil terbaik pengelompokkan. Metode K-Means dapat menjadi alternatif dalam membuat model analisis monitoring persediaan obat di Puskemas.
- 20 June 2022
- Published by State University of Medan in CESS (Journal of Computer Engineering, System and Science)
- Vol. 7 (2) , 537-546
Open AccessDrugs Consumption Clustering Model using K-Means Technique
Persediaan obat pada suatu Puskesmas seringkali habis sebelum jadwal penerimaan obat dilakukan hal ini dikarenakan Kejadian Luar Biasa (KLB). Sehingga, perencanaan persediaan obat yang efektif dan efisien dengan menerapkan metode kecerdasan buatan dalam rangka membantu pihak manajemen sangat diperlukan. Penelitian ini bertujuan untuk memonitoring persediaan obat sebagai salah satu dasar dalam permintaan obat. Data pemakaian obat yang digunakan berasal dari Laporan Pemakaian dan Lembar Permintaan Obat (LPLPO) UPTD Puskesmas Lempake tahun 2016-2018 dan telah dinormalisasi dengan metode Z-Score. Metode K-Means telah diterapkan sebanyak 3 cluster terdiri tinggi (C1), sedang (C2) dan kurang (C3) dimana penentuan titik centroid berdasarkan nilai max, average, dan min. Sedangkan, metode jarak Euclidean distance telah ditetapkan untuk menganalisis jarak data tiap cluster. Hasil temuan mengindikasikan bahwa pengujian cluster menggunakan Sum of Squared Error (SSE) telah mendapatkan nilai sebesar 77,34814. Dimana, hasil pengelompokkan yaitu C1 sebanyak 5 data, C2 sebanyak 14 data, dan C3 sebanyak 206 data. Hal ini berarti bahwa 3 cluster merupakan hasil terbaik pengelompokkan. Metode K-Means dapat menjadi alternatif dalam membuat model analisis monitoring persediaan obat di Puskemas.
- Open Access
- 20 December 2021
- Published by Universitas Hamzanwadi in EDUMATIC: Jurnal Pendidikan Informatika
- Vol. 5 (2) , 352-361
Prototype System Water Level Reservoir untuk Pengendalian Kelebihan Air dengan Mikrokontroller Arduino Uno R3
PDAM Loa Kulu Branch still uses sticks or poles as an indicator of the water level in the reservoir. Reservoir is a place to store clean water production from PDAM, the weakness of using sticks or poles is when the operator does not monitor continuously causing air loss when production becomes large. The goal of the study was to design a water-level prototype to control excess water in the reservoir. The method used is a prototype with the stage of gathering information through interviewing PDAM staff, creating and repairing prototypes and testing prototypes. The test used hardware consisting of Arduino uno r3, ultrasonic sensor hc-sr04, flowmeter sensor yf-s201, 16 x 2 lcd, relay module, buzzer, solenoid valve 12 V_dc, pump 12 V_dc and display measurement results in the visual studio application 2019. Our findings are that the length of reservoir charging with an average input discharge of 3.6 liters / minute is 2.93 minutes. As for the length of emptying the reservoir with an average output discharge of 1.06 liters / minute is 12.10 minutes. The conclusion of this study is that the system can monitor the water level inside the reservoir automatically and know the time needed for the feeling and emptying process of the reservoir.
- 20 December 2021
- Published by Universitas Hamzanwadi in EDUMATIC: Jurnal Pendidikan Informatika
- Vol. 5 (2) , 352-361
Open AccessPrototype System Water Level Reservoir untuk Pengendalian Kelebihan Air dengan Mikrokontroller Arduino Uno R3
PDAM Loa Kulu Branch still uses sticks or poles as an indicator of the water level in the reservoir. Reservoir is a place to store clean water production from PDAM, the weakness of using sticks or poles is when the operator does not monitor continuously causing air loss when production becomes large. The goal of the study was to design a water-level prototype to control excess water in the reservoir. The method used is a prototype with the stage of gathering information through interviewing PDAM staff, creating and repairing prototypes and testing prototypes. The test used hardware consisting of Arduino uno r3, ultrasonic sensor hc-sr04, flowmeter sensor yf-s201, 16 x 2 lcd, relay module, buzzer, solenoid valve 12 V_dc, pump 12 V_dc and display measurement results in the visual studio application 2019. Our findings are that the length of reservoir charging with an average input discharge of 3.6 liters / minute is 2.93 minutes. As for the length of emptying the reservoir with an average output discharge of 1.06 liters / minute is 12.10 minutes. The conclusion of this study is that the system can monitor the water level inside the reservoir automatically and know the time needed for the feeling and emptying process of the reservoir.
- Open Access
- 20 December 2021
- Published by Universitas Hamzanwadi in EDUMATIC: Jurnal Pendidikan Informatika
- Vol. 5 (2) , 352-361
Prototype System Water Level Reservoir untuk Pengendalian Kelebihan Air dengan Mikrokontroller Arduino Uno R3
PDAM Loa Kulu Branch still uses sticks or poles as an indicator of the water level in the reservoir. Reservoir is a place to store clean water production from PDAM, the weakness of using sticks or poles is when the operator does not monitor continuously causing air loss when production becomes large. The goal of the study was to design a water-level prototype to control excess water in the reservoir. The method used is a prototype with the stage of gathering information through interviewing PDAM staff, creating and repairing prototypes and testing prototypes. The test used hardware consisting of Arduino uno r3, ultrasonic sensor hc-sr04, flowmeter sensor yf-s201, 16 x 2 lcd, relay module, buzzer, solenoid valve 12 V_dc, pump 12 V_dc and display measurement results in the visual studio application 2019. Our findings are that the length of reservoir charging with an average input discharge of 3.6 liters / minute is 2.93 minutes. As for the length of emptying the reservoir with an average output discharge of 1.06 liters / minute is 12.10 minutes. The conclusion of this study is that the system can monitor the water level inside the reservoir automatically and know the time needed for the feeling and emptying process of the reservoir.
- 20 December 2021
- Published by Universitas Hamzanwadi in EDUMATIC: Jurnal Pendidikan Informatika
- Vol. 5 (2) , 352-361
Open AccessPrototype System Water Level Reservoir untuk Pengendalian Kelebihan Air dengan Mikrokontroller Arduino Uno R3
PDAM Loa Kulu Branch still uses sticks or poles as an indicator of the water level in the reservoir. Reservoir is a place to store clean water production from PDAM, the weakness of using sticks or poles is when the operator does not monitor continuously causing air loss when production becomes large. The goal of the study was to design a water-level prototype to control excess water in the reservoir. The method used is a prototype with the stage of gathering information through interviewing PDAM staff, creating and repairing prototypes and testing prototypes. The test used hardware consisting of Arduino uno r3, ultrasonic sensor hc-sr04, flowmeter sensor yf-s201, 16 x 2 lcd, relay module, buzzer, solenoid valve 12 V_dc, pump 12 V_dc and display measurement results in the visual studio application 2019. Our findings are that the length of reservoir charging with an average input discharge of 3.6 liters / minute is 2.93 minutes. As for the length of emptying the reservoir with an average output discharge of 1.06 liters / minute is 12.10 minutes. The conclusion of this study is that the system can monitor the water level inside the reservoir automatically and know the time needed for the feeling and emptying process of the reservoir.