Ariana Purnomo

Mrs. Ariana Purnomo

National Taiwan University of Science and Technology
orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 May 2021 in Sensors
Verified
Journal Article
Open access
PDF file
APAriana Purnomo
Ariana Purnomo
DLDing-Bing Lin
Ding-Bing Lin
Tjahjo AdiprabowoTjahjo Adiprabowo
Tjahjo Adiprabowo
Willy Fitra HendriaWilly Fitra Hendria
Willy Fitra Hendria
During the pandemic of coronavirus disease-2019 (COVID-19), medical practitioners need non-contact devices to reduce the risk of spreading the virus. People with COVID-19 usually experience fever and have difficulty breathing. Unsupervised care to patients with respiratory problems will be the main reason for the rising death rate. Periodic linearly increasing frequency chirp, known as frequency-modulated continuous wave (FMCW), is one of the radar technologies with a low-power operation and high-resolution detection which can detect any tiny movement. In this study, we use FMCW to develop a non-contact medical device that monitors and classifies the breathing pattern in real time. Patients with a breathing disorder have an unusual breathing characteristic that cannot be represented using the breathing rate. Thus, we created an Xtreme Gradient Boosting (XGBoost) classification model and adopted Mel-frequency cepstral coefficient (MFCC) feature extraction to classify the breathing pattern behavior. XGBoost is an ensemble machine-learning technique with a fast execution time and good scalability for predictions. In this study, MFCC feature extraction assists machine learning in extracting the features of the breathing signal. Based on the results, the system obtained an acceptable accuracy. Thus, our proposed system could potentially be used to detect and monitor the presence of respiratory problems in patients with COVID-19, asthma, etc.

11 July 2022 in IEEE Sensors Journal
Verified
Journal Article
Closed access
APAloysius Adya Pramudita
Aloysius Adya Pramudita
DLDing-Bing Lin
Ding-Bing Lin
SHSung-Nien Hsieh
Sung-Nien Hsieh
EAErfansyah Ali
Erfansyah Ali
HRHarfan Hian Ryanu
Harfan Hian Ryanu
APAriana Purnomo
Ariana Purnomo
The presence of an obstacle in detecting respiration vital signs using a radar system does not only exhibit attenuation and phase shift effects on the radar signal but also causes additional beat frequencies to appear beside those from the target. When a conventional FMCW radar system detects the peak of the received signal spectrum as a beat frequency, this will give an error of detection. The respiratory vital signs will then be undetectable. A method to overcome this obstacle problem is needed. Therefore the implementation of the FMCW radar system in detecting respiratory vital signs behind the wall can be realized. In this paper, a method to deal with the previously mentioned problem is proposed. The proposed method consists of a method for identifying the obstacle response. Then the results are used to eliminate the beat frequency that arises from the obstacle structure, and therefore the signal to clutter ratio (SCR) can be improved. Furthermore, the method is combined with the phase detection method, which is applied to extract the Doppler response related to the target respiratory vital signs. The weighting process by elaborating cross correlation is also employed for minimizing clutter from other objects reflection under debris. A laboratory experiment by developing an FMCW radar system with a 24 GHz frequency operation was performed in this research. The proposed detection method was elaborated in the post-processing of the radar system. The experiment result demonstrates that the proposed method is capable of eliminating the effect of the wall and successfully extracting the respiration vital sign pattern.

19 July 2022 in IEEE Transactions on Biomedical Circuits and Systems
Verified
Journal Article
Closed access
APAriana Purnomo
Ariana Purnomo
KKKokoy Siti Komariah
Kokoy Siti Komariah
DLDing-Bing Lin
Ding-Bing Lin
Willy Fitra HendriaWilly Fitra Hendria
Willy Fitra Hendria
BSBong-Kee Sin
Bong-Kee Sin
Nur AhmadiNur Ahmadi
Nur Ahmadi
A respiratory disorder that attacks COVID-19 patients requires intensive supervision of medical practitioners during the isolation period. A non-contact monitoring device will be a suitable solution for reducing the spread risk of the virus while monitoring the COVID-19 patient. This study uses Frequency-Modulated Continuous Wave (FMCW) radar and Machine Learning (ML) to obtain respiratory information and analyze respiratory signals, respectively. Multiple subjects in a room can be detected simultaneously by calculating the Angle of Arrival (AoA) of the received signal and utilizing the Multiple Input Multiple Output (MIMO) of FMCW radar. Fast Fourier Transform (FFT) and some signal processing are implemented to obtain a breathing waveform. ML helps the system to analyze the respiratory signals automatically. This paper also compares the performance of several ML algorithms such as Multinomial Logistic Regression (MLR), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGB), Light Gradient Boosting Machine (LGBM), CatBoosting (CB) Classifier, Multilayer Perceptron (MLP), and three proposed stacked ensemble models, namely Stacked Ensemble Classifier (SEC), Boosting Tree-based Stacked Classifier (BTSC), and Neural Stacked Ensemble Model (NSEM) to obtain the best ML model. The results show that the NSEM algorithm achieves the best performance with 97.1% accuracy. In the real-time implementation, the system could simultaneously detect several objects with different breathing characteristics and classify the respiratory signals into five different classes.

20 January 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Tjahjo AdiprabowoTjahjo Adiprabowo
Tjahjo Adiprabowo
DLDing-Bing Lin
Ding-Bing Lin
TWTse-Hsuan Wang
Tse-Hsuan Wang
APAriana Purnomo
Ariana Purnomo
APAloysius Adya Pramudita
Aloysius Adya Pramudita
The measurement of heartbeat rate and breathing rate for patients with sensitive skin, such as skin with burns, is very difficult to do, especially if the number of patients is large and medical personnel is limited. Therefore, this study seeks to propose a preliminary solution to this problem by proposing a device that can measure the vital signs of several people concurrently, especially the heartbeat rate and breathing rate, without attaching sensors to their skin. This is done using an FMCW (frequency-modulated continuous wave) radar that operates at 77–81 GHz. FMCW radar emits electromagnetic waves towards the chest of several targets and picks up the reflected waves. Then, using signal processing of these reflected waves, each target’s heartbeat rate and breathing rate can be obtained. Our experiment managed to perform concurrent detection for four targets. The experimental results are between 52 and 82 beats per minute for the heartbeat rates and between 10 and 35 breaths per minute for the breathing rates of four targets. These results are in accordance with normal heartbeat rate and normal breathing rate; thus, our research succeeded in proposing a preliminary solution to this problem.

13 January 2023 in Informatics
Verified
Journal Article
Open access
PDF file
KKKokoy Siti Komariah
Kokoy Siti Komariah
APAriana Purnomo
Ariana Purnomo
ASArdianto Satriawan
Ardianto Satriawan
MHMuhammad Ogin Hasanuddin
Muhammad Ogin Hasanuddin
CSCasi Setianingsih
Casi Setianingsih
BSBong-Kee Sin
Bong-Kee Sin
To pursue a healthy lifestyle, people are increasingly concerned about their food ingredients. Recently, it has become a common practice to use an online recipe to select the ingredients that match an individual’s meal plan and healthy diet preference. The information from online recipes can be extracted and used to develop various food-related applications. Named entity recognition (NER) is often used to extract such information. However, the problem in building an NER system lies in the massive amount of data needed to train the classifier, especially on a specific domain, such as food. There are food NER datasets available, but they are still quite limited. Thus, we proposed an iterative self-training approach called semi-supervised multi-model prediction technique (SMPT) to construct a food ingredient NER dataset. SMPT is a deep ensemble learning model that employs the concept of self-training and uses multiple pre-trained language models in the iterative data labeling process, with a voting mechanism used as the final decision to determine the entity’s label. Utilizing the SMPT, we have created a new annotated dataset of ingredient entities obtained from the Allrecipes website named FINER. Finally, this study aims to use the FINER dataset as an alternative resource to support food computing research and development.

26 June 2024 in Journal of Community Services: Sustainability and Empowerment
Verified
Journal Article
Open access
PDF file
RDRafie Djajasoepena
Rafie Djajasoepena
ISIwan Setiawan
Iwan Setiawan
MBMuhammad Agni Catur Bhakti
Muhammad Agni Catur Bhakti
APAriana Purnomo
Ariana Purnomo
MAMedia A Ayu
Media A Ayu
WWWandy Wandy
Wandy Wandy
Artificial Intelligence (AI) is now commonly used in many sectors, including education. Utilizing AI technology to support learning does not mean replacing the role of educators. The critical role of educators is to teach, educate, and train students to build their skills, knowledge, and morals, which are irreplaceable by AI. SMP Negeri 174 Jakarta is a public junior high school in East Jakarta and would like to receive guidance to upgrade teachers’ competencies in AI. The event lasted half a day and about 39 teachers participated in this agenda. The overall community service activities began in early April 2024 and ended on May 15, 2024, and all main activities were completed 100%. The session was successfully delivered in around two hours with days of preparations. Future recommendation is to include similar topics related to academic activities and technology.