IoT-Based Logistic Robot for Real-Time Monitoring and Control Patients during COVID-19 Pandemic

Hafidz, Isa; Adiputra, Dimas; Montolalu, Billy; Prastyabudi, Wahyu Andy; Widyantara, Helmy; Afandi, Mas Aly

doi:10.25077/jnte.v9n3.810.2020

Cited by 4 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Penelitian yang diusulkan memiliki sudut pandang lain [27] di mana sudut pandang yang diambil adalah pengolahan data di mana data pembacaan parameter inframerah diolah terlebih dahulu dengan regresi linear sebelum digunakan sebagai hasil akhir pembacaan [28]. Metode regresi linear sendiri telah banyak diterapkan untuk peningkatan akurasi di berbagai sensor seperti sensor kelembapan, sensor pH, dan sensor intensitas cahaya [29][30] [31]. Penelitian ini memanfaatkan jarak sebagai variabel bebas dan suhu sebagai variabel terikat memiliki dugaan peningkatan akurasi dari pengukuran suhu berbasis inframerah.…”

Section: Pendahuluanunclassified

Estimasi Galat Sebagai Kompensasi Hasil Pembacaan Sensor Suhu Non-Sentuh Menggunakan Regresi Linier

Purnama¹,

Afandi²,

Selamet³

et al. 2023

View full text Add to dashboard Cite

Abstrak Penelitian ini bertujuan untuk membuktikan penerapan metode regresi linear untuk mengestimasi galat sebagai kompensasi untuk menurunkan galat pembacaan sensor suhu non-sentuh. Hal ini terlihat pada masa pandemi COVID – 19 melalui penggunaan thermo gun untuk mengukur suhu seseorang membutuhkan jarak yang sangat dekat. Penelitian dilakukan dengan mengukur objek air yang merupakan unsur terbanyak pada tubuh manusia. Suhu pengukuran telah dikondisikan pada 36°C, 37°C, dan 38°C dengan masing-masing variasi jarak 2cm, 4cm, dan 6cm. Hasil dari validasi menunjukkan model dapat menurunkan galat pada suhu 36°C pada masing-masing jarak sebesar 4,43%, 8,00%, dan 8,70% pada jarak 2cm, 4cm, dan 6cm. Validasi berdasarkan MAE sebelum dimodelkan adalah 2,91 dan nilai MAE setelah dimodelkan adalah 0,37. Penurunan nilai galat pada suhu 37°C untuk masing-masing jarak 2cm, 4cm, dan 6cm adalah 5,94%, 8,72%, dan 7,34%. Nilai validasi berdasarkan MAE sebelum dimodelkan adalah 3,02 dan nilai MAE setelah dimodelkan adalah 0,27. Penurunan nilai galat pada suhu 38°C untuk masing-masing jarak 2cm, 4cm, dan 6cm adalah 6,27%, 8,67%, dan 11,03%. Nilai validasi berdasarkan MAE sebelum dilakukan permodelan adalah 3,87 dan nilai MAE setelah dimodelkan adalah 0,57. Berdasarkan data tersebut dapat disimpulkan bahwa estimasi galat sebagai kompensasi hasil pembacaan sensor suhu non-sentuh mampu menurunkan galat hasil pembacaan sensor.

show abstract

Section: Pendahuluanunclassified

Estimasi Galat Sebagai Kompensasi Hasil Pembacaan Sensor Suhu Non-Sentuh Menggunakan Regresi Linier

Purnama¹,

Afandi²,

Selamet³

et al. 2023

View full text Add to dashboard Cite

show abstract

“…A confusion matrix is a special table that allows you to visualize the performance of your algorithm. This method has four frameworks for fall detection systems as measurements [21]. Among them are true positives (TP).…”

Section: Device Test Designmentioning

confidence: 99%

Enabling Guardian Angels: Designing and Constructing a Wireless Nurse CallSystem with IMU-Based Fall Detection for Enhanced Patient Safety

Al Farouq,

Cholif Arrohman Nurriduwan

2023

JNTE

View full text Add to dashboard Cite

Falling poses a significant health concern across all age groups, with particular severityamong the elderly. Hospitalized patients, in particular, are vulnerable to injuries andevendeath due to falls. While patient supervision is essential for fall prevention, constant proximitybetween patients and healthcare staff is not always feasible. To tackle this challenge, thisstudy aimed to develop a solution that enables immediate assistance for patients who aredistant from the nurse call button when a fall occurs.The study employed the IMU sensor,which combines an accelerometer and a gyroscope. This sensor served as a transmitter todetect gravity acceleration and magnitude when afall event takes place. Thedata obtainedfrom the IMU sensor were further processed using an Arduino Uno microcontroller. Thesensor was integrated into a belt worn around the waist of the participants, who performedvarious movements such as falling facing down, falling up, falling to the right, falling to theleft, standing then sitting, and sitting then standing.The experimental tests yielded compellingresults, with all trials achieving an accuracy rate of 81.7%. The accuracy was determined byanalyzing the confusion matrix, which enabled accurate calculations.The utilization of thisinnovative tool significantly reduces the risk of patients experiencing detrimental outcomesfollowing falls by promptly notifying medical personnel, even when they aredistant from thenurse call button. Moreover, the implementation of this tool enhances overall safety forhospitalized patients, especially those at a high risk of falling. Future research can explore theintegration of additional sensors or the development of more sophisticated algorithms tofurther enhancethe accuracy and efficacy of this tool.

show abstract

“…COVID-19 first case in 2019 and became a pandemic in 2020 until 2022 [10]. Several devices and products, such as robotic logistics for helping nurses treat COVID-19 patients [11], COVID-19 vaccines [12] [13], and COVID-19 fast detections [14]. The COVID-19 pandemic has changed human activity in many aspects, especially studying activities in every school [15].…”

Section: Introductionmentioning

confidence: 99%

Improvement of Student Attendance System for Recording Student Surface Body Temperature Based on Internet of Things

Afandi¹,

Enriko²,

Baihaqy³

2023

ELINVO

View full text Add to dashboard Cite

Student attendance is a system used for tracking student activity in school. Many methods are used to develop student attendance systems, such as Quick Response (QR) Code systems, Radio Frequency Identification (RFID) systems, fingerprint systems, and so on. The COVID-19 pandemic has driven technological development, especially in the student attendance system. Measuring human surface body temperature has become a protocol that must be done before entering school. Student attendance systems need to expand the function not only for attendance but also for monitoring student surface body temperature. This research aims to improve student attendance systems by adding surface body temperature measurements and recording during student presence. Recording data can be done by using the internet of things. Student presence data will be sent to school databases throughout the internet. This system uses RFID technology for student presence and a non-contact thermal sensor for temperature measurement. According to data research, non-contact thermal sensors provide a temperature reading with an average error of 1.69%, a minimum error value of 0.96%, and a maximum error value of 2.57% with a range error value of 0.35°C – 0.95°C. RFID test shows that the optimum distance for the system to read an RFID card is 0 – 2cm. The System also successfully sent presence data to the student school database through the internet. This study concludes that developed systems can track student attendance by recording the student’s surface body temperature while in presence. Further work will be focused on managing data networks if this system is used with many users in the school.

show abstract

IoT-Based Logistic Robot for Real-Time Monitoring and Control Patients during COVID-19 Pandemic

Cited by 4 publications

References 4 publications

Estimasi Galat Sebagai Kompensasi Hasil Pembacaan Sensor Suhu Non-Sentuh Menggunakan Regresi Linier

Estimasi Galat Sebagai Kompensasi Hasil Pembacaan Sensor Suhu Non-Sentuh Menggunakan Regresi Linier

Enabling Guardian Angels: Designing and Constructing a Wireless Nurse CallSystem with IMU-Based Fall Detection for Enhanced Patient Safety

Improvement of Student Attendance System for Recording Student Surface Body Temperature Based on Internet of Things

Contact Info

Product

Resources

About