Herminarto Nugroho
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Herminarto Nugroho has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
Ade Irawan
1 shared publicationAriana Yunita
Departement of Computer Science Faculty of Science and Computer Pertamina University Jalan Teuku Nyak Arief Simprug Kebayoran Lama Jakarta Selatan 12220 Indonesia
1 shared publication- Ariana Yunita
Program Studi Ilmu Komputer, Universitas Pertamina, Jalan Teuku Nyak Arief, Simprug, DKI Jakarta, Indonesia, 12220
1 shared publication - Aulia Rahma Annisa
Universitas Pertamina, Indonesia
1 shared publication Erwin Setiawan
Universitas Pertamina Jakarta Indonesia
1 shared publicationHandoyo Suryo Laksono
Universitas Pertamina
1 shared publication
Latest Publications
- Open Access
- 14 October 2026
- Published by Universitas Nurul Jadid in Journal of Electrical Engineering and Computer (JEECOM)
- Vol. 8 (3) , 113-123
Physics-Informed Deep Sequential Learning and Non-Parametric Adaptive Thresholding for Integrated Microgrid Fault Detection
The rapid proliferation of clean energy microgrids—integrating solar photovoltaic (PV) generation, bidirectional power converters, and battery energy storage systems (BESS)—requires robust fault detection and isolation (FDI) to guarantee continuous operational stability. However, non-Gaussian residual profiles caused by severe irradiance intermittency and dynamic switching transients compromise traditional fixed-threshold strategies, resulting in elevated false alarm and missed detection rates. To address this challenge, this study presents a hybrid FDI framework combining physics-guided deep sequential forecasting with non-parametric adaptive thresholding. A Temporal Convolutional Network integrated with Long Short-Term Memory (TCN-LSTM), constrained by equivalent circuit and DC bus power balance equations, is developed to forecast multi-modal nominal trajectories and extract reliable diagnostic residuals. Raw electrical streams sampled at 10 kHz are down sampled via moving-window averaging to 10-second intervals to accommodate prognostic forecasting horizons. Non-parametric Kernel Density Estimation (KDE) is subsequently implemented to dynamically compute adaptive threshold boundaries from empirical non-Gaussian residual distributions. Simulation experiments under stochastic irradiance profiles and dynamic load cycles confirm that the proposed TCN-LSTM architecture achieves nominal forecasting RMSE values of 0.007 V for cell voltage and 0.306 °C for temperature, reducing the missed detection rate of PV shading mismatches and critical sensor biases compared to static thresholding. Furthermore, integration with a Local Outlier Factor (LOF) anomaly detector provides early warning margins of 83.5 minutes for micro-short circuit voltage dips and 24.6 minutes for thermal runaway precursors prior to hard-limit BMS alarms.
- 14 October 2026
- Published by Universitas Nurul Jadid in Journal of Electrical Engineering and Computer (JEECOM)
- Vol. 8 (3) , 113-123
Open AccessPhysics-Informed Deep Sequential Learning and Non-Parametric Adaptive Thresholding for Integrated Microgrid Fault Detection
The rapid proliferation of clean energy microgrids—integrating solar photovoltaic (PV) generation, bidirectional power converters, and battery energy storage systems (BESS)—requires robust fault detection and isolation (FDI) to guarantee continuous operational stability. However, non-Gaussian residual profiles caused by severe irradiance intermittency and dynamic switching transients compromise traditional fixed-threshold strategies, resulting in elevated false alarm and missed detection rates. To address this challenge, this study presents a hybrid FDI framework combining physics-guided deep sequential forecasting with non-parametric adaptive thresholding. A Temporal Convolutional Network integrated with Long Short-Term Memory (TCN-LSTM), constrained by equivalent circuit and DC bus power balance equations, is developed to forecast multi-modal nominal trajectories and extract reliable diagnostic residuals. Raw electrical streams sampled at 10 kHz are down sampled via moving-window averaging to 10-second intervals to accommodate prognostic forecasting horizons. Non-parametric Kernel Density Estimation (KDE) is subsequently implemented to dynamically compute adaptive threshold boundaries from empirical non-Gaussian residual distributions. Simulation experiments under stochastic irradiance profiles and dynamic load cycles confirm that the proposed TCN-LSTM architecture achieves nominal forecasting RMSE values of 0.007 V for cell voltage and 0.306 °C for temperature, reducing the missed detection rate of PV shading mismatches and critical sensor biases compared to static thresholding. Furthermore, integration with a Local Outlier Factor (LOF) anomaly detector provides early warning margins of 83.5 minutes for micro-short circuit voltage dips and 24.6 minutes for thermal runaway precursors prior to hard-limit BMS alarms.
- Open Access
- 30 November 2024
- Published by Universitas Ahmad Dahlan in Buletin Ilmiah Sarjana Teknik Elektro
- Vol. 6 (4) , 392-400
Gray Level Co-Occurrence Matrix (GLCM)-based Feature Extraction for Rice Leaf Diseases Classification
In this paper, we propose Gray Level Co-Occurrence Matrix (GLCM) based Feature Extraction to identify and classify rice leaf diseases. An Artificial Neural Network (ANN) algorithm is used to train a classification model. Various statistical features such as energy, contrast, homogeneity, and correlation are extracted from the GLCM matrix to describe the image texture features. After feature removal, an ANN classification model was trained using a dataset consisting of images of healthy and diseased rice leaves. The ANN training process involves optimizing weights and bias using backpropagation to achieve accurate classification. After training, the ANN model is tested using split test data to measure classification performance. The experimental results show that the GLCM method is effective in helping improve accuracy, validation of accuracy, loss, validation of loss, precision, and recall.
- 30 November 2024
- Published by Universitas Ahmad Dahlan in Buletin Ilmiah Sarjana Teknik Elektro
- Vol. 6 (4) , 392-400
Open AccessGray Level Co-Occurrence Matrix (GLCM)-based Feature Extraction for Rice Leaf Diseases Classification
In this paper, we propose Gray Level Co-Occurrence Matrix (GLCM) based Feature Extraction to identify and classify rice leaf diseases. An Artificial Neural Network (ANN) algorithm is used to train a classification model. Various statistical features such as energy, contrast, homogeneity, and correlation are extracted from the GLCM matrix to describe the image texture features. After feature removal, an ANN classification model was trained using a dataset consisting of images of healthy and diseased rice leaves. The ANN training process involves optimizing weights and bias using backpropagation to achieve accurate classification. After training, the ANN model is tested using split test data to measure classification performance. The experimental results show that the GLCM method is effective in helping improve accuracy, validation of accuracy, loss, validation of loss, precision, and recall.
- Open Access
- 1 January 2023
- Published by Sekolah Tinggi Teknik-PLN in Energi & Kelistrikan
- Vol. 14 (2) , 196-206
Analisis Komparasi Jenis Teknologi Elektrolisis Hidrogen Sebagai Alternatif Energi Bersih di Indonesia
Hidrogen merupakan salah satu alternatif energi bersih yang dapat diaplikasikan di Indonesia. Tapi hidrogen perlu diproduksi dikarenakan tidak tersedia di alam secara bebas. Salah satu cara memproduksi hidrogen adalah melalui proses elektrolisis. Ada beberapa jenis teknologi elektrolisis yang tersedia pada saat ini dan masing-masing memiliki kelebihan dan kekurangan. Dari beberapa teknologi ini, dipilih dua jenis yang paling sesuai untuk diterapkan di Indonesia, yaitu Solid Oxide Electrolysis Cell (SOEC) dan Membrane Free Electrolysis (MFE). Pemilihan dua teknologi ini mempertimbangkan tingkat efisiensi kelistrikan dan potensi sumber energi yang ada di Indonesia. SOEC yang bekerja dengan memanfaatkan suhu tinggi sangat cocok diaplikasikan bersandingan dengan pembangkit listrik tenaga panas bumi. Sedangkan MFE memiliki efisiensi kelistrikan yang tinggi dan biaya maintenance yang relatif lebih murah sehingga cocok diaplikasikan dengan memanfaatkan tenaga surya.
- 1 January 2023
- Published by Sekolah Tinggi Teknik-PLN in Energi & Kelistrikan
- Vol. 14 (2) , 196-206
Open AccessAnalisis Komparasi Jenis Teknologi Elektrolisis Hidrogen Sebagai Alternatif Energi Bersih di Indonesia
Hidrogen merupakan salah satu alternatif energi bersih yang dapat diaplikasikan di Indonesia. Tapi hidrogen perlu diproduksi dikarenakan tidak tersedia di alam secara bebas. Salah satu cara memproduksi hidrogen adalah melalui proses elektrolisis. Ada beberapa jenis teknologi elektrolisis yang tersedia pada saat ini dan masing-masing memiliki kelebihan dan kekurangan. Dari beberapa teknologi ini, dipilih dua jenis yang paling sesuai untuk diterapkan di Indonesia, yaitu Solid Oxide Electrolysis Cell (SOEC) dan Membrane Free Electrolysis (MFE). Pemilihan dua teknologi ini mempertimbangkan tingkat efisiensi kelistrikan dan potensi sumber energi yang ada di Indonesia. SOEC yang bekerja dengan memanfaatkan suhu tinggi sangat cocok diaplikasikan bersandingan dengan pembangkit listrik tenaga panas bumi. Sedangkan MFE memiliki efisiensi kelistrikan yang tinggi dan biaya maintenance yang relatif lebih murah sehingga cocok diaplikasikan dengan memanfaatkan tenaga surya.
- 31 October 2022
- Published by Universitas Muria Kudus in Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer
- Vol. 12 (1) , 47-56
Group Delay Optimization in Cascaded Optical Ring Ressonator-based Optical Beamforming Networks
Cascaded optical ring resonator-based optical beamforming networks can be used to optimize the signal power received by planes. This is essential for airplanes-sattelite communication as a solution for a high-speed internet access inside airplanes cabin. This system relies on phased array antenna (PAA), an array of a very small and flat antenna elements which will receive a time-delayed version of desired signal from specific angle. The delay time will create phase differences between each received signal, and in consequence, lower the signal power. We propose a method to optimize the group delay of the received signals in order to obtain maximum signal power. We simulate the optimization algorithm using a set of data, which consists of full input signals. To analyze the accuracy, the desired signal is known explicitly. Given the configuration of OBFNs and all nominal parameters required, it was verified in simulation that the optimization algorithm can be used to tune optical beamforming networks for any group delays.
- 31 October 2022
- Published by Universitas Muria Kudus in Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer
- Vol. 12 (1) , 47-56
Group Delay Optimization in Cascaded Optical Ring Ressonator-based Optical Beamforming Networks
Cascaded optical ring resonator-based optical beamforming networks can be used to optimize the signal power received by planes. This is essential for airplanes-sattelite communication as a solution for a high-speed internet access inside airplanes cabin. This system relies on phased array antenna (PAA), an array of a very small and flat antenna elements which will receive a time-delayed version of desired signal from specific angle. The delay time will create phase differences between each received signal, and in consequence, lower the signal power. We propose a method to optimize the group delay of the received signals in order to obtain maximum signal power. We simulate the optimization algorithm using a set of data, which consists of full input signals. To analyze the accuracy, the desired signal is known explicitly. Given the configuration of OBFNs and all nominal parameters required, it was verified in simulation that the optimization algorithm can be used to tune optical beamforming networks for any group delays.
- Open Access
- 28 February 2020
- Published by Faculty of Computer Science, Universitas Indonesia in Jurnal Ilmu Komputer dan Informasi
- Vol. 13 (1) , 9-15
Fully Convolutional Variational Autoencoder For Feature Extraction Of Fire Detection System
This paper proposes a fully convolutional variational autoencoder (VAE) for features extraction from a large-scale dataset of fire images. The dataset will be used to train the deep learning algorithm to detect fire and smoke. The features extraction is used to tackle the curse of dimensionality, which is the common issue in training deep learning with huge datasets. Features extraction aims to reduce the dimension of the dataset significantly without losing too much essential information. Variational autoencoders (VAEs) are powerfull generative model, which can be used for dimension reduction. VAEs work better than any other methods available for this purpose because they can explore variations on the data in a specific direction.
- 28 February 2020
- Published by Faculty of Computer Science, Universitas Indonesia in Jurnal Ilmu Komputer dan Informasi
- Vol. 13 (1) , 9-15
Open AccessFully Convolutional Variational Autoencoder For Feature Extraction Of Fire Detection System
This paper proposes a fully convolutional variational autoencoder (VAE) for features extraction from a large-scale dataset of fire images. The dataset will be used to train the deep learning algorithm to detect fire and smoke. The features extraction is used to tackle the curse of dimensionality, which is the common issue in training deep learning with huge datasets. Features extraction aims to reduce the dimension of the dataset significantly without losing too much essential information. Variational autoencoders (VAEs) are powerfull generative model, which can be used for dimension reduction. VAEs work better than any other methods available for this purpose because they can explore variations on the data in a specific direction.
- Open Access
- 24 December 2018
- Published by International Association of Online Engineering (IAOE) in International Journal of Interactive Mobile Technologies (iJIM)
- Vol. 12 (8) , 96-103
The Relationship between Mobile Phone Usage in Classroom and Academic Achievement in College Life
The use of mobile phone has been increasing nowadays in most part of the world and it has become the phenomenon where people cannot live without. This study aims to reveal whether mobile phone use affects student’s academic achievement compared to other factors such as study program, student’s focus and gender. The frequent of mobile phone use and how excellence student’s academic performance will be analysed. A survey has been conducted to a large number of college students. A questionnaire was developed and delivered by online questionnaire to 513 students of Universitas Pertamina, Jakarta, Indonesia. Using Ordinary Least Square’s result statistical analysis, it can be concluded that gender and study program have significant effects to GPA, while the use of mobile phone and its effect of distracting student’s focus are not significant to GPA. Furthermore , female students significantly scored higher GPA result by 0.23 point than male students, cateris paribus. Then, students from social sciences have higher GPA results by 0.2 point than students from engineering sciences, cateris paribus. Generally, the results should be interesting for decision maker in academic field on how important to embrace mobile phone for learning style.
- 24 December 2018
- Published by International Association of Online Engineering (IAOE) in International Journal of Interactive Mobile Technologies (iJIM)
- Vol. 12 (8) , 96-103
Open AccessThe Relationship between Mobile Phone Usage in Classroom and Academic Achievement in College Life
The use of mobile phone has been increasing nowadays in most part of the world and it has become the phenomenon where people cannot live without. This study aims to reveal whether mobile phone use affects student’s academic achievement compared to other factors such as study program, student’s focus and gender. The frequent of mobile phone use and how excellence student’s academic performance will be analysed. A survey has been conducted to a large number of college students. A questionnaire was developed and delivered by online questionnaire to 513 students of Universitas Pertamina, Jakarta, Indonesia. Using Ordinary Least Square’s result statistical analysis, it can be concluded that gender and study program have significant effects to GPA, while the use of mobile phone and its effect of distracting student’s focus are not significant to GPA. Furthermore , female students significantly scored higher GPA result by 0.23 point than male students, cateris paribus. Then, students from social sciences have higher GPA results by 0.2 point than students from engineering sciences, cateris paribus. Generally, the results should be interesting for decision maker in academic field on how important to embrace mobile phone for learning style.
- Open Access
- 1 August 2018
- Published by Universitas Ahmad Dahlan in TELKOMNIKA (Telecommunication Computing Electronics and Control)
- Vol. 16 (4) , 1607-1615
Deep Learning for Tuning Optical Beamforming Networks
Deep Learning for Tuning Optical Beamforming Networks
- 1 August 2018
- Published by Universitas Ahmad Dahlan in TELKOMNIKA (Telecommunication Computing Electronics and Control)
- Vol. 16 (4) , 1607-1615
Open AccessDeep Learning for Tuning Optical Beamforming Networks
Deep Learning for Tuning Optical Beamforming Networks