Dien Rahmawati
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Dien Rahmawati has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Wahmisari Priharti
Advanced Biomedical Intelligent Engineering Laboratory, Biomedical & Healthcare Technology Center of Excellence, School of Electrical Engineering, Telkom University, Bandung, Indonesia
2 shared publications Agus Nurhidayat
1 shared publicationDana Aulia
1 shared publicationDaniel P.P. Mbarep
1 shared publication- Ega Elfira
School of Electrical Engineering, Telkom University, Indonesia
1 shared publication Faisal Budiman
1 shared publication
Latest Publications
- Open Access
- 3 August 2026
- Published by Poltekkes Kemenkes Surabaya in Journal of Electronics, Electromedical Engineering, and Medical Informatics
- Vol. 8 (4) , 1687-1701
Embedded Colour- and Electrodermal-Based Pressure Injury Staging and Objective Pain Assessment System Powered by a Proton Battery
Pressure injury is a serious health concern among the elderly and individuals with restricted mobility and is often associated with pain that reduces quality of life. Conventional assessment relies on clinician visual inspection and subjective pain scales, which are difficult to apply to patients with limited communication abilities. Therefore, early identification, accurate stage classification and objective pain assessment are essential for effective clinical intervention. This study develops an embedded pressure injury stage classification and pain assessment system integrating a colour sensor and an electrodermal activity (EDA) sensor with a Rule-Based Decision Tree to classify pressure injuries into four clinical stages, powered by a six-cell 1.5 V proton battery pack as an alternative to conventional lithium-based power sources. The system achieved an overall accuracy, precision, recall, and F1-score of 0.88, 0.89, 0.88, and 0.88, respectively. Skin Conductance Level (SCL) increased progressively from Stage 1 to Stage 3 and decreased at Stage 4, indicating a preliminary physiological pattern associated with injury severity. The battery pack maintained a stable output voltage of 9.1 V at an average current consumption of 279.9 mA, demonstrating its feasibility as an alternative power source. Because the thresholds were derived from 70 annotated Medetec images and validated on only two subjects with four injury sites (40 region-level measurements), the reported metrics should be interpreted as preliminary proof-of-concept rather than definitive clinical validation, and larger studies are needed for clinical confirmation.
- 3 August 2026
- Published by Poltekkes Kemenkes Surabaya in Journal of Electronics, Electromedical Engineering, and Medical Informatics
- Vol. 8 (4) , 1687-1701
Open AccessEmbedded Colour- and Electrodermal-Based Pressure Injury Staging and Objective Pain Assessment System Powered by a Proton Battery
Pressure injury is a serious health concern among the elderly and individuals with restricted mobility and is often associated with pain that reduces quality of life. Conventional assessment relies on clinician visual inspection and subjective pain scales, which are difficult to apply to patients with limited communication abilities. Therefore, early identification, accurate stage classification and objective pain assessment are essential for effective clinical intervention. This study develops an embedded pressure injury stage classification and pain assessment system integrating a colour sensor and an electrodermal activity (EDA) sensor with a Rule-Based Decision Tree to classify pressure injuries into four clinical stages, powered by a six-cell 1.5 V proton battery pack as an alternative to conventional lithium-based power sources. The system achieved an overall accuracy, precision, recall, and F1-score of 0.88, 0.89, 0.88, and 0.88, respectively. Skin Conductance Level (SCL) increased progressively from Stage 1 to Stage 3 and decreased at Stage 4, indicating a preliminary physiological pattern associated with injury severity. The battery pack maintained a stable output voltage of 9.1 V at an average current consumption of 279.9 mA, demonstrating its feasibility as an alternative power source. Because the thresholds were derived from 70 annotated Medetec images and validated on only two subjects with four injury sites (40 region-level measurements), the reported metrics should be interpreted as preliminary proof-of-concept rather than definitive clinical validation, and larger studies are needed for clinical confirmation.
- 16 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 13, 313-318
Analysis of LoRa (Long Range) Performance as The Development of Remote Communication for Earthquake Detection Systems in High-rise Buildings
Earthquakes are defined as natural disasters with a severe impact on the surrounding environment. However, it is very often that the process of disaster mitigation information is not spread by conveying it to the public due to power outages and damaged communication networks. In this regard, there is a communication technology; Long Range (LoRa) which focuses on communication systems designed for wireless Local Area intercommunication, and long-distance communication with low power. but the evaluation and analysis of LoRa performance in the real world with specific case studies became a mini research topic. This research sought to assess and analyze LoRa performance as applied to a case study of an earthquake detection system in a high-rise building. The indication of the signal strength of the RSSI, quality of signal transmission with noise in the transmission of data information SNR, Delay in data transmission, and Packet Loss were some parameters assessed. LoRa communication technology on the earthquake detection system shows the performance to be able to send information data up to the 1st floor with a distance of 15 m in high-rise buildings when the LoRa gateway is on the 4th floor, but good signal conditions and a small percentage of packet loss can only be achieved up to the 2nd floor with a distance of 10 m with LoRa gateway, then send data packets at intervals fastest on a 1 s transmission speed, the signal is still good. There is only a 10% packet loss.
- 16 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 13, 313-318
Analysis of LoRa (Long Range) Performance as The Development of Remote Communication for Earthquake Detection Systems in High-rise Buildings
Earthquakes are defined as natural disasters with a severe impact on the surrounding environment. However, it is very often that the process of disaster mitigation information is not spread by conveying it to the public due to power outages and damaged communication networks. In this regard, there is a communication technology; Long Range (LoRa) which focuses on communication systems designed for wireless Local Area intercommunication, and long-distance communication with low power. but the evaluation and analysis of LoRa performance in the real world with specific case studies became a mini research topic. This research sought to assess and analyze LoRa performance as applied to a case study of an earthquake detection system in a high-rise building. The indication of the signal strength of the RSSI, quality of signal transmission with noise in the transmission of data information SNR, Delay in data transmission, and Packet Loss were some parameters assessed. LoRa communication technology on the earthquake detection system shows the performance to be able to send information data up to the 1st floor with a distance of 15 m in high-rise buildings when the LoRa gateway is on the 4th floor, but good signal conditions and a small percentage of packet loss can only be achieved up to the 2nd floor with a distance of 10 m with LoRa gateway, then send data packets at intervals fastest on a 1 s transmission speed, the signal is still good. There is only a 10% packet loss.
- Open Access
- 8 December 2022
- Published by Poltekkes Kemenkes Surabaya in Jurnal Teknokes
- Vol. 15 (4) , 197–205
Comparison of GLCM and First Order Feature Extraction Methods for Classification of Mammogram Images
Breast cancer is one of the main causes of death in women and ranks first in cancer cases in Indonesia. Therefore, an early detection and prevention of breast cancer is necessary, one of which is through mammography procedures. A machine learning classifier such as Support Vector Machines (SVM) could be used as an aid to the doctors and radiologist in diagnosing breast cancer from the mammogram images. The aim of this paper is to compare two feature extraction methods used in SVM, namely the Gray Level Co-Occurrence Matrix (GLCM) and first order with two kernels for each method, namely Gaussian and Polynomial. Classification using SVM method is carried out by testing several parameters such as the value of C, gamma, degree and varying the pixel spacing values in GLCM, which usually in previous studies only used the default pixel spacing. The dataset consists of 500 mammogram images containing 250 benign and malignant images, respectively. This study is expected to find out the best method with the highest accuracy between these two texture feature extractions and and able to distinguish between benign and malignant classes correctly. The result achieved that Gray Level Co-Occurrence Matrix (GLCM) feature extraction method with both Gaussian and Polynomial kernel yields the best performance with an accuracy of 89%.
- 8 December 2022
- Published by Poltekkes Kemenkes Surabaya in Jurnal Teknokes
- Vol. 15 (4) , 197–205
Open AccessComparison of GLCM and First Order Feature Extraction Methods for Classification of Mammogram Images
Breast cancer is one of the main causes of death in women and ranks first in cancer cases in Indonesia. Therefore, an early detection and prevention of breast cancer is necessary, one of which is through mammography procedures. A machine learning classifier such as Support Vector Machines (SVM) could be used as an aid to the doctors and radiologist in diagnosing breast cancer from the mammogram images. The aim of this paper is to compare two feature extraction methods used in SVM, namely the Gray Level Co-Occurrence Matrix (GLCM) and first order with two kernels for each method, namely Gaussian and Polynomial. Classification using SVM method is carried out by testing several parameters such as the value of C, gamma, degree and varying the pixel spacing values in GLCM, which usually in previous studies only used the default pixel spacing. The dataset consists of 500 mammogram images containing 250 benign and malignant images, respectively. This study is expected to find out the best method with the highest accuracy between these two texture feature extractions and and able to distinguish between benign and malignant classes correctly. The result achieved that Gray Level Co-Occurrence Matrix (GLCM) feature extraction method with both Gaussian and Polynomial kernel yields the best performance with an accuracy of 89%.