Giva Andriana Mutiara

Dr. Giva Andriana Mutiara

orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
22 September 2016
Verified
Conference Paper
Closed access
GMGiva Andriana Mutiara
Giva Andriana Mutiara
GHGita Indah Hapsari
Gita Indah Hapsari
RRRamanta Rijalul
Ramanta Rijalul
Cane is a tool that used by blind people or someone who has visually impaired which is caused by an accident or an illness. Cane helps the blind people to check whether there are any obstacles around them. However, before doing the research, we conducted a questionnaire to the blind people about what kind of extension module that would be implemented on their cane. Based-on the result, they need an extension smart tools for their cane that can give information about hitch, obstacle, hole, and also the direction of compass wind position to guide their way and also inform them Qibla direction. This research designed a prototype named Smart Guide Extension that can detect obstacles, holes and give information about eights wind direction using Arduino. The obstacles and holes module uses 2 PING Sensors, while the 8 direction of the wind information uses CMP compass sensor 511. All the information will be informed through the sound. The results of testing the obstacle data module stated that the buzzer will be active at a distance of 150 cm-3 cm and the speed of beep sound faster from 1.1 until 0.3 seconds. The test holes modules state that the beep sound active at a distance of 10-50 cm. The system can detect eight direction of the compass wind position with deviation angle position about ±3°. Based on the questionnaire of trial prototype to the responder, 77.38% of responder stated these tools are user friendly and easily to used.

1 May 2017
Verified
Conference Paper
Closed access
GHGita Indah Hapsari
Gita Indah Hapsari
GMGiva Andriana Mutiara
Giva Andriana Mutiara
DKDicky Tiara Kusumah
Dicky Tiara Kusumah
Visually impaired have a deficiency in their vision which has limitations in terms of mobility. On the other side, the blind must also run their daily activities. Sometimes, the blind must performs a mobility from one building to another building in some area which has a distance like campus, mall and others. In order to make the visually impaired mobility becomes easier, we created a tool that can help them to detect the location of the destination buildings or inform them where the position of the standing place through the sound as the output information. Prototype made using the GPS module, keypad, earphone and raspberry Pi. The results show that the functional testing tools can detect the location area of interest with a deviation of less than 8 m. Also based on the friendly user testing, this prototype categorized good enough to be used by the blind.

28 March 2022 in Journal of Biomimetics, Biomaterials and Biomedical Engineering
Verified
Journal Article
Closed access
PDF file
FFFahrurrasyid Fahrurrasyid
Fahrurrasyid Fahrurrasyid
GHGita Indah Hapsari
Gita Indah Hapsari
LMLisda Meisaroh
Lisda Meisaroh
GMGiva Andriana Mutiara
Giva Andriana Mutiara
In Indonesia, motorcycle traffic accidents have increased rapidly. Traffic accidents result in high mortality. One of the causes is influenced by human psychological factors or human error. However, to improve the behavior of the riders and due reducing traffic accidents, the purpose of this research is developed a Smart Helmet that can detect drowsiness by measuring the heartbeats psychological riders. Besides that, this system equipped with an SOS button. Its function is to detect and help the riders if there were any emergency incidents on the roads. This proposed system designed using a heartbeat pulse sensor, GPS module, GSM module, Arduino Nano, push-button, and buzzer. Smart Helmet examined in several scenarios to test the performance of the drowsiness and the SOS button. The resulting test on 10 respondents defined that the drowsiness can be detected and give a buzzer alert when the heartbeat is below 60 bpm. The information can be seen without delay. The incident location can be tracked down by utilizing the google maps application. The shift position as the error distance of the GPS incident location only happens in the range of 21.96-42.63 meters. The conclusion is the helmet can detect drowsiness based on heartrate and give an alarm. The SOS button is functionally properly as long as the helmet is used in the outdoor area.

1 January 2019 in Procedia Computer Science
Verified
Journal Article
Open access
RFRatna Juwita Fauziah
Ratna Juwita Fauziah
GMGiva Andriana Mutiara
Giva Andriana Mutiara
PPPeriyadi Periyadi
Periyadi Periyadi

19 September 2025 in IEEE Access
Verified
Journal Article
Open access
ASAl Fahri Suhaimi
Al Fahri Suhaimi
GMGiva Andriana Mutiara
Giva Andriana Mutiara
MRMochammad Fahru Rizal
Mochammad Fahru Rizal
The development of efficient and real-time animal behavior monitoring systems is crucial to support precision livestock farming. This study proposes a behavior classification system for sheep using a triaxial accelerometer and embedded machine learning models, implemented on a low-power Internet of Things (IoT) device. Accelerometer signals were filtered using a Kalman Filter and segmented with a 2-second moving average window with 50% overlap. From each window, statistical features including mean, standard deviation, minimum, maximum, and signal energy were extracted for each axis (X, Y, Z), resulting in a 15-feature vector per segment. Four classification algorithms such as Random Forest (RF), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and XGBoost were evaluated for recognizing three sheep behaviors: standing, laying, and sleeping. Experimental results on a dataset of 6,000 labeled samples showed that Random Forest outperformed other models with an accuracy of 92.1% and an F1-score of 0.9272. The trained model was then converted and deployed on an ESP32 Mini C3 microcontroller, allowing real-time behavior classification directly on the device. Classified data was transmitted via Wi-Fi and visualized on a web dashboard with latency under 2 seconds. The system demonstrates that lightweight machine learning models can be effectively integrated into embedded platforms for autonomous animal behavior monitoring. This approach reduces the reliance on manual observation and enables scalable implementation in practical farm environments. Future enhancements include incorporating additional sensor modalities expanding behavior classes and adopting adaptive learning techniques to improve robustness in diverse and dynamic livestock settings.

1 January 2014 in Contemporary Engineering Sciences
Verified
Journal Article
Open access
GMGiva Andriana Mutiara
Giva Andriana Mutiara
GHGita Indah Hapsari
Gita Indah Hapsari
RHRini Handayani
Rini Handayani