Article Per Year (5 Year)
p-Index From 2020 - 2025
3.472
P-Index
This Author published in this journals
All Journal Rotasi Bulletin of Electrical Engineering and Informatics Journal of Mechanical Engineering Science and Technology INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi Knowledge Engineering and Data Science Journal of Energy, Mechanical, Material and Manufacturing Engineering Journal of Electronics, Electromedical Engineering, and Medical Informatics Buletin Ilmiah Sarjana Teknik Elektro Journal of Robotics and Control (JRC) Jurnal Teknik Informatika (JUTIF) International Journal of Robotics and Control Systems Mechanical Engineering for Society and Industry Proceeding International Pelita Bangsa Journal of Environment and Sustainability Education Control Systems and Optimization Letters Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Jurnal Teknokes
Wahyu Caesarendra
Dosen Jurusan Teknik Mesin, Fakultas Teknik, Universitas Diponegoro
Aerospace Engineering Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Materials Science & Nanotechnology Mechanical Engineering Physics Transportation Other

Published : 29 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 29 Documents
Search

 1   2   3 
Remaining useful life prognosis of low-speed slew bearing using random vector functional link Caesarendra, Wahyu; Rahardja, Dimas Revindra; Abdillah, Muhammad; Darmanto, Seno; Handayani, Sri Utami; Lestari, Wahyu Dwi; Krolczyk, Grzegorz
Mechanical Engineering for Society and Industry Vol 5 No 1 (2025)
Publisher : Universitas Muhammadiyah Magelang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31603/mesi.12965

Abstract

Bearings have a very important role in an industry. However, the cost of maintenance and replacement of bearings are very expensive especially for slew-bearing which operated in a very low speed. If the low-speed slew bearing shutdown suddenly, it will also cause a financial issue to the certain industries with rely on the rotating machines because the entire machine will be shut down and the production will be stop Therefore, monitoring of the low-speed slew bearing condition at all times is necessary to predict the bearing failure. There has been advance monitoring devices and systems related to the vibration condition monitoring for bearing and rotating machines, however, in certain cases those monitoring devices and systems are not sufficient. Machine learning is offered to complement and contribute in this case which aims to determine the prediction and Remaining Useful Life (RUL) of the bearing before the bearing experiences more damage. In this paper, the Random Vector Functional Link (RVFL) is used to predict RUL using low speed slew bearing data from University of Wollongong, Australia. The main evaluation matrix such as RMSE is used as an evaluation of the performance of the model used. According to the prediction results, the best modeling results are obtained using a data ratio of 80:20 and a SELU activation function that produces the best average RMSE value. The prediction value of Remaining Useful Life (RUL) of the bearing is 94.24%.
Evaluation of the Impact of SMOTEENN on Monkeypox Case Classification Performance Using Boosting Algorithms Siena, Laifansan; Saragih, Triando Hamonangan; Nugroho, Radityo Adi; Kartini, Dwi; Muliadi; Caesarendra, Wahyu
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol. 7 No. 2 (2025): May
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/ijeeemi.v7i2.77

Abstract

Monkeypox is a zoonotic disease with increasing global prevalence, posing a significant challenge in healthcare. Its widespread transmission necessitates more accurate detection systems to assist medical professionals in diagnosing and managing cases effectively. One of the main challenges in developing monkeypox prediction models is class imbalance in datasets, which can cause models to favor the majority class and reduce predictive accuracy for rarer cases. To address this issue, this study evaluates the effectiveness of the SMOTEENN resampling technique in improving the classification performance of monkeypox cases. Three boosting algorithms Gradient Boosting, XGBoost, and LightGBM were applied to a monkeypox dataset consisting of 25,000 samples. The data preprocessing steps included handling missing values, feature encoding, and feature scaling. The dataset was then balanced using SMOTEENN, a hybrid technique combining the Synthetic Minority Over-sampling Technique (SMOTE) and Edited Nearest Neighbors (ENN). Additionally, hyperparameter tuning with GridSearchCV was performed to optimize model performance by systematically selecting the best parameter combinations. The results indicate that applying SMOTEENN significantly improved classification accuracy, achieving a maximum of 69%, with an F1-score of 67%. Compared to previous studies, the proposed approach demonstrated superior performance in handling class imbalance and enhancing classification robustness. These findings highlight the potential of SMOTEENN and boosting algorithms in medical data classification, particularly for infectious diseases with imbalanced datasets. This study contributes to the development of more reliable machine learning techniques for improving disease detection, classification accuracy, and overall model generalization. Future research should explore additional resampling techniques, deep learning architectures, and feature selection methods to further improve predictive performance in medical diagnostics.
Improving Classification Accuracy of Breast Ultrasound Images Using Wasserstein GAN for Synthetic Data Augmentation Mas Diyasa, I Gede Susrama; Humairah, Sayyidah; Puspaningrum, Eva Yulia; Durry, Fara Disa; Lestari, Wahyu Dwi; Caesarendra, Wahyu; Dewi, Deshinta Arrova; Aryananda, Rangga Laksana
Journal of Robotics and Control (JRC) Vol. 6 No. 4 (2025)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v6i4.25075

Abstract

Breast cancer remains one of the most prevalent cancers in Indonesia, and early detection plays a vital role in improving patient outcomes. Ultrasound imaging is a non-invasive and accessible technique used to classify breast conditions into normal, benign, or malignant categories. The advancement of deep learning, particularly Transfer Learning with Convolutional Neural Networks (CNNs), has significantly enhanced the performance of automated image classification. However, the effectiveness of CNNs heavily relies on large, balanced datasets—resources that are often limited and imbalanced in medical domains. To address this issue, this study explores the use of Wasserstein Generative Adversarial Networks (WGAN) for synthetic data augmentation. WGAN is capable of learning the underlying distribution of real ultrasound images and generating high-quality synthetic samples. The inclusion of the Wasserstein distance stabilizes training, with convergence observed around 2500–3000 epochs out of 5000. While synthetic data improves classifier performance, there remains a potential risk of overfitting, particularly when the synthetic images closely mirror the training data. Compared to traditional augmentation techniques such as rotation, flipping, and scaling, WGAN-generated data provides more diverse and realistic representations. Among the tested models, VGG16 achieved the highest accuracy of 83.33% after WGAN augmentation. Nonetheless, computational resource limitations posed challenges in training stability and duration. Furthermore, issues related to model generalizability, as well as ethical and patient privacy considerations in using synthetic medical data, must be addressed to ensure responsible deployment in real-world clinical settings.
Comparison of Time Series Algorithms Using SARIMA and Prophet in Predicting Short-Term Bitcoin Prices Brilliant, Muhammad Zidan; Widiyaningtyas, Triyanna; Caesarendra, Wahyu
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 4 (2025): JUTIF Volume 6, Number 4, Agustus 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.4.4773

Abstract

Digital finance, particularly Bitcoin, has become a global phenomenon with high volatility, posing great challenges for traders in predicting short-term prices. This study compares the performance of the SARIMA and Prophet algorithms in predicting short-term Bitcoin prices using daily closing price data from October 1, 2014, to October 1, 2024. The study utilizes two different data timeframes, a 10-year dataset (2014-2024) and the last 5 years (2019-2024) for comparative analysis. The SEMMA methodology is used to analyze and compare the two algorithms, which consist of the stages Sample, Explore, Modify, Model, and Assess. The experimental results show that SARIMA provides more stable and consistent results with an MAPE value of 1.24% and RMSE of 896.15 in Scenario 1 and an MAPE value of 1.27% and RMSE of 920.24 in Scenario 2. In contrast, Prophet shows different performance in each scenario. In Scenario 1, Prophet shows optimal results but not so good with an average MAPE of 1.74% and an RMSE value of 1214.86. On the other hand, Prophet showed good performance in Scenario 2 with a lower average MAPE of 0.71% and a smaller RMSE of 489.94, indicating Prophet's ability to handle newer and more dynamic datasets. Both models show their respective advantages; SARIMA is better for long and stable historical data, while Prophet is more effective for shorter and dynamic data. This research provides practical insights for traders and investors in choosing the right prediction model, with results for further study in predicting crypto asset prices.
Optimizing Type 2 Diabetes Classification with Feature Selection and Class Balancing in Machine Learning Wantoro, Agus; Yuliana, Aviv Fitria; Andini, Dwi Yana Ayu; Awaliyani, Ikna; Caesarendra, Wahyu
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 4 (2025): JUTIF Volume 6, Number 4, Agustus 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.4.5166

Abstract

Type 2 Diabetes (T2DM) is a crucial factor in patient survival and treatment effectiveness. Errors in diabetes detection lead to disease severity, high costs, prolonged healing time, and a decline in service quality. Additionally, a major challenge in developing Machine Learning (ML)-based detection decision support systems is the class imbalance in medical data as well as the high feature dimensionality that can affect the accuracy and efficiency of the model. This research proposes an approach based on feature selection (FS) and handling class imbalance to improve performance in type 2 diabetes. Several feature selection techniques such as Information Gain (IG), Gain Ratio (GR), Gini Decrease (GD), Chi-Square (CS), Relief-F, and FCBF can perform feature selection based on weighting ranking. Furthermore, to address the imbalanced class distribution, we utilize the Synthetic Minority Over-Sampling Technique (SMOTE). ML classification models such as Support Vector Machine (SVM), Gradient Boosting (GB), Tree, Neural Network (NN), Random Forest (RF), and AdaBoost were tested and evaluated based on the confusion matrix including accuracy, precision, recall, and time. The experimental results show that the combination of strategies for handling imbalanced classes significantly improves the predictive performance of ML algorithms. In addition, we found that the combination of feature selection techniques IG+AdaBoost consistently demonstrates optimal performance. This study emphasizes the importance of data preprocessing and the selection of the right algorithms in the development of machine learning-based T2DM detection systems. Accurate detection can reduce the severity of disease, lower treatment costs, speed up the healing process, and improve healthcare services.
Development of a High Flow Oxygen Analyzer for Monitoring Oxygen Therapy in Adults Using High Flow Nasal Cannula (HFNC) Silvian, Fawaida; Dian Setioningsih, Endang Dian Setioningsih1; Triwiyanto , Triwiyanto; Caesarendra, Wahyu
Jurnal Teknokes Vol. 17 No. 2 (2024): June
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Side effects of using HFNC include gastric insufflation (air entry into the stomach) because HFNC increases positive airway. The next side effect of using HFNC is complications of pneumothorax and pneumomediastinum. This complication occurs in the case of children. In these cases, oxygen administration was reported to exceed the recommended protocol. Although the incidence of air leaks in the use of HFNC for adults has not been reported, similar events may also occur in adults, so close monitoring is needed, especially on oxygen flow. Making the design of the High Flow Oxygen Analyzer can be used for monitoring the flow and oxygen concentration in HFNC. This study uses an Arduino microcontroller to process the oxygen concentration output from the OOA101-1 oxygen concentration sensor, then the processed oxygen concentration will be displayed on the TFT LCD. The variable in this study is the oxygen concentration setting value, while the independent variable is the OOA101-1 oxygen concentration sensor. The concentration value was adjusted using an oxygen blender, while the comparison tool used was gas flow analysis (Citrex H3). In the testing phase, the measurement value is 50% to 100% with a time of 1 minute at each point. Based on the measurements that have been made, the largest error value is obtained at a concentration of 50%, which is 3.07% and the smallest error value is at 100%, which is 0.40%. Dataretrieval using a compressor and central oxygen is very influential on the results of the flow and oxygen concentration. The results obtained are more stable than without the use of a compressor and central oxygen. From these results, the calibrator module has an error (value) which is still within the relative limits of the conclusion, which is ±5%. And also the design of this tool is portable and low cost and made for use in hospital companies as maintenance of HFNC equipment.
Analysis Infinite Impulse Response Filter for Reducing Motion Artifacts in Heart Rate Signals Based on Photoplethysmography Fadillah, Wa Ode Nurul; Ariswati, Her Gumiwang; Caesarendra, Wahyu
Jurnal Teknokes Vol. 17 No. 3 (2024): September
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The increasing prevalence of motion artifacts (MA) in photoplethysmography (PPG) signals poses significantchallenges for accurate heart rate monitoring, particularly in dynamic environments. This study addresses the problem of MAinterference in PPG signals, which can lead to erroneous heart rate readings and compromised patient monitoring. To mitigatethis issue, we employed an Infinite Impulse Response (IIR) filter to enhance the quality of PPG signals by effectively reducingthe impact of motion artifacts. The methodology involved collecting PPG signals from a sample of participants during variousphysical activities. The raw signals were subjected to both filtering and non-filtering processes using MATLAB, allowing fora comparative analysis of the signal quality. The filtering process was designed to suppress unwanted frequencies associatedwith motion while preserving the physiological signals of interest. The performance of the IIR filter was evaluated based onthe Signal-to-Noise Ratio (SNR) and the accuracy of heart rate extraction. Results indicated a significant improvement insignal quality post-filtering, with the SNR increasing from an average of 5.2 dB to 15.8 dB, demonstrating a substantialenhancement in the clarity of the PPG signals. Furthermore, the heart rate extraction accuracy improved from 78% to 95%after applying the IIR filter, showcasing the effectiveness of the proposed method in real-time applications. In conclusion, theapplication of the IIR filter in processing PPG signals effectively reduces motion artifacts, leading to more accurate heart ratemonitoring. This research highlights the potential for improved patient outcomes in clinical settings and suggests furtherexploration of advanced filtering techniques to enhance the reliability of wearable health monitoring devices. The findingsunderscore the importance of addressing motion artifacts in the development of robust biomedical sensing technologies.
Exploring Digital Filters for Cardiac Monitoring: A Focus on Carotid Pulse and Phonocardiogram Signals Ramadhan, Bahrurrizki; Yulianto, Endro; Luthfiyah, Sari; Caesarendra, Wahyu
Jurnal Teknokes Vol. 17 No. 1 (2024): March
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Heart defect early detection and correct diagnosis have become important healthcare priorities. Tools for monitoring cardiac problems are constantly being developed, with the PCG (Phonocardiogram) and Cardiac Monitor via Carotid Pulse essential for heart evaluation. Although condenser microphones embedded in electric stethoscopes have been used in past research as PCG sensors, more advancements are still required to reduce received noise. This study investigates how well a Chebyshev type-II digital filter works to reduce noise on the cardiac monitor using PCG and carotid pulse. The PCG sensor is the GY-MAX 9814 module, which is interfaced with an Arduino Uno microcontroller. Matlab, Visual Studio (used as a graph viewer), and Doppler Simulator (used as a phantom cardiac signal) are used. SNR (Signal to Noise Ratio) is used in the analysis to assess the effectiveness of two digital filter orders. The average SNR value for the Doppler Simulator is 0.001404 dB at order 2, however, it climbs dramatically to 18.60023 dB at level 4 according to the results of the SNR analysis. The average SNR value in human signals is 11.50718 dB before the filter, 0.001404 dB after the post-order 2 filter, and 12.0009 dB after the post-order 4 filter. According to the results, the digital filter of order 4 is more effective in reducing noise. This study highlights the possibility of an order 4 digital filter to improve the Cardiac Monitor through PCG and Carotid Pulse. Through enhanced signal quality, the creation of this gadget holds the potential for streamlining the identification of cardiac problems. Future developments in this technology could lead to more precise and trustworthy cardiac exams, which would help with early diagnosis and treatment of cardiovascular health.
Comparative Analysis of LSTM and GRU for River Water Level Prediction Faris, Fakhri Al; Taqwa, Ahmad; Handayani, Ade Silvia; Husni, Nyayu Latifah; Caesarendra, Wahyu; Asriyadi, Asriyadi; Novianti, Leni; Rahman, M. Arief
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 5 (2025): JUTIF Volume 6, Number 5, Oktober 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.5.5054

Abstract

Accurate river water level prediction is essential for flood management, especially in tropical areas like Palembang. This study systematically analyzes the performance of two deep learning models, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), for real-time water level forecasting using hourly rainfall and water level data collected from automatic sensors. A series of experiments were conducted by varying window sizes (10, 20, 30) and the number of layers (1, 2, 3) for both models, with model performance assessed using RMSE, MAE, MAPE, and NSE. The results demonstrate that both window size and network depth significantly influence prediction accuracy and computational efficiency. The LSTM model achieved its highest accuracy with a window size of 30 and a single layer, while the GRU model performed best with a window size of 20 and two layers. This work contributes by systematically analyzing hyperparameter configurations of LSTM and GRU models on hourly rainfall and water level time series for flood-prone regions, offering empirical insight into parameter tuning in recurrent neural architectures for hydrological forecasting. These findings highlight the importance of careful parameter selection in developing reliable early warning systems for flood risk management.
Co-Authors Abdullayev, Vugar Achmad Widodo Ade Silvia Handayani Agus Sudarmanto Agus Wantoro Ahmad Rofii Ahmad Taqwa Ahmed, Abdussalam Ali Alfian Ma’arif Anant Athavale, Vijay Andini, Dwi Yana Ayu Ariesma Githa Giovany Ariswati, Her Gumiwang Aryananda, Rangga Laksana Asriyadi Asriyadi Brilliant, Muhammad Zidan Busono Soerowirdjo Dewi, Deshinta Arrova Dian Setioningsih, Endang Dian Setioningsih1 Dwi Kartini Dwi Kartini, Dwi DWI RAMADHANI Edison, Rizki Edmi Endro Yulianto Eva Yulia Puspaningrum Fadillah, Wa Ode Nurul Faikul Umam Faiza, Linda Ziyadatul Fara Disa Durry Faris, Fakhri Al Fatma Indriani Fitriana, Lutfatul Furizal, Furizal Gołdasz, Iwona Gupta, Munish Kumar Herianto Herianto Hidayat, Fathur Rachman Humairah, Sayyidah Ichwan Dwi Nugraha Ikna Awaliyani Irwan Budiman Irwan Budiman Joga Dharma Setiawan Krolczyk, Grzegorz Leni Novianti Luthfiyah, Sari Maharani, Siti Mutia Mahmood, Muhammad Azim Mahmud Mahmud MAJDOUBI, Rania Mas Diyasa, I Gede Susrama Mochammad Ariyanto Mochammad Denny Surindra Muhammad Abdillah Muhammad Fuad Muhammad Reza Faisal, Muhammad Reza Muliadi Nyayu Latifah Husni, Nyayu Latifah Pamanasari, Elta Diah Pranoto, Kirana Astari Putri, Farika Radityo Adi Nugroho Rahardja, Dimas Revindra Rahman, M. Arief Ramadhan, Bahrurrizki Ramadhan, Yogi Reza REKIK, Chokri Rozaq, Hasri Akbar Awal Rudi Irawan Sagita, Muhamad Rian Samudra, Alan Saragih, Triando Hamonangan Seno Darmanto Septiani, Fahira Setiawan, Joga D Setiawan, Nurman Siena, Laifansan Silvian, Fawaida Sitompul, Carlos R Sri Hastuty, Sri Sri Utami Handayani Sumarti, Heni Suwarno, Iswanto Triwiyanto , Triwiyanto Triyanna Widiyaningtyas Utomo, Bedjo V.H, Abdullayev W, Kusnanto Mukti Wahyu Dwi Lestari YILDIZ, Oktay Yuliana, Aviv Fitria Zy, Ahmad Turmudi