Garuda - Garba Rujukan Digital

ANALISIS PERFORMANSI ALGORITMA SVM, CNN, DAN LSTM UNTUK PENGENALAN KEGIATAN MANUSIA DENGAN URAD FMCW RADAR Azhar Yunda Ramadhan; Figo Azzam De Fitrah; Muhammad Adi Nurhidayat; Fiky Yosep Suratman; Istiqomah Istiqomah
TEKTRIKA Vol 8 No 1 (2023): TEKTRIKA Vol.8 No.1 2023
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/tektrika.v8i1.6312

In this study, we compare Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Long ShortTerm Memory (LSTM) algorithms as commonly used machine learning algorithms based on FMCW Radar data for Human Activity Recognition (HAR). The comparison is conducted by evaluating the models on test data and considering the fitting time and the number of parameters required by each model to achieve the desired results, to find the most efficient model that provides the best results. We discovered that the LSTM 01 model with one layer of 16 unit-LSTM produces the best result based on the scoring of several tested models. The model demonstrated an ability to achieve accuracy up to 86% on the test data with a relatively small number of parameters, i.e., 294,725. Key Words: Radar, computation, FMCW, SVM, CNN, LSTM.

PENGEMBANGAN PENGENALAN AKTIVITAS MANUSIA UNTUK LANSIA BERDASARKAN NILAI AKSELEROMETER DAN FITUR STATISTIK Azzahra Nadya Kahpiasa; Istiqomah Istiqomah; Husneni Mukhtar
TEKTRIKA Vol 8 No 1 (2023): TEKTRIKA Vol.8 No.1 2023
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/tektrika.v8i1.6669

Elderly people are those who are 60 years of age or older. Elderly people are more likely to fall due to age-related reductions in physiological processes, particularly bone and muscular functions. Falling is one of the symptoms that can be lethal. These effects may cause mortality if prompt medical assistance is not received due to the deterioration in numerous organ functions required to maintain body homeostasis. Previous studies have tested the Random Forest model from acceleration and gyroscope measurements to identify human activity. In this research, feature extraction was carried out utilizing variables such as maximum, minimum, mean, median, kurtosis, skewness, and variance that were obtained from the Acceleration data from accelerometer sensor in type IMU LSM9DS1. The Acceleration data include Acceleration X, Acceleration Y, Acceleration Z and Acceleration Magnitude. To evaluate the effectiveness of the Decision Tree model, cross-validation will be employed. The best feature extraction values were Magnitude Acceleration Variance, X Acceleration Maximum, Magnitude Acceleration Maximum, Z Acceleration Median, and Z Acceleration Variance, with a Decision Tree model accuracy rate of 99.8%. Key Words: Elderly, Fall, Tendency to Fall, Decision Tree, Statistical Feature

REMOTE LABORATORY BERBASIS PROTOKOL VIRTUAL NETWORK COMPUTING SEBAGAI MEDIA PEMBELAJARAN JARAK JAUH PROGRAMMABLE LOGIC CONTROLLER Isa Rachman; Muhammad Khoirul Hasin; Ryan Yudha Adhitya; Mohammad Basuki Rahmat; Adianto Adianto; Agus Nurcahyo; Dewi Rizani Ruwahida
TEKTRIKA Vol 8 No 1 (2023): TEKTRIKA Vol.8 No.1 2023
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/tektrika.v8i1.6044

One effective method that can be applied to online practical learning during the COVID-19 pandemic is remote laboratory which is a combination of the real world and the virtual world using the internet network. This research aims to design remote laboratory based on the Virtual Network Computing (VNC) on Programmable Logic Controller (PLC) which is one of the regular practical devices used in Industrial Automation Laboratory. Remote laboratory in the form of a remote laboratory website for administrators consisting of user management and course management; and for users it consists of login, course and schedule, user order and remote desktop containing PLC Trainer, XG5000 and camera. From the results of remote laboratory testing starting from registration, remote laboratory website, login, course selection, suitability of course schedules, user order and remote desktop can be accessed so that the designed remote laboratory can work properly. The existence of a delay time of 0,52–1,73 seconds for the results of shooting by the camera as a display visualization for online monitoring of practice activities in the laboratory on the client computer is influenced by the condition of the internet network used mainly on server computers. Key Words: practice, online, remote, laboratory, VNC, PLC.

IDENTIFIKASI KARAKTERISTIK MATERIAL DARI BAHAN BATIK TRADISIONAL INDONESIA Harfan Hian Ryanu; Ummi Jumria; Hawary Siddik; Muhammad Daffa Hamsy; Nabila Rizqa Damayanti; Regita Nurul Fauziah; Bambang Setia Nugroho; Levy Olivia Nur
TEKTRIKA Vol 8 No 1 (2023): TEKTRIKA Vol.8 No.1 2023
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/tektrika.v8i1.6062

Wearable antenna has an important role in WBAN (Wireless Body Area Network) as the main component that supports on-body communication. This study focuses on the characterization of Material Under Test (MUT) from Indonesian traditional batik material using the CSRR (Complementary split ring resonator) sensor extraction method. The frequency response and magnitude of S21 are used to extract the relative permittivity and loss tangent of the material. From all the responses that appear, a simulation and measurement of wearable antennas is carried out with a working frequency of 2.4. GHz. The antenna with the most similar simulation and measurement results is then selected as a candidate for relative permittivity and loss tangent of the material. From all the 6 frequency responses that emerged from CSRR sensor measurements, the relative permittivity value of 2.083 and the loss tangent of 0.144 achieved a good similarity between the measurement and simulation with an accuracy rate of 99.17%. The final design of the proposed wearable antenna is also validated to transmit heart rate data using the ESP32 microcontroller to the internet using a 2.4 GHz frequency Wifi access point. Key Words: Wearable antenna, extraction of material characteristics, wireless body area network (WBAN), CSRR, material under test, vital signs

PENINGKATAN EFEKTIFITAS KUALITAS KANDANG AYAM MENGGUNAKAN INTERNET OF THINGS Mia Rsomiati; M.Riko Trisaputra; Adelia Nurul Solihah
TEKTRIKA Vol 8 No 1 (2023): TEKTRIKA Vol.8 No.1 2023
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/tektrika.v8i1.5953

Chicken is one of the poultry that is familiar among the public. There are several things that need to be considered when raising chickens. One of them is the condition of the cage. In addition to the conditions of the cage, the influence of temperature, humidity and ammonia gas levels also affect the growth of the chickens. This is quite difficult for breeders who must regularly go to the pen to ensure the temperature, humidity and ammonia gas levels remain at ideal numbers. So, a system was created that can help monitor and control the chicken coop by utilizing Internet of Things (IoT) technology to display information on temperature, humidity, and ammonia gas levels in the chicken coop. This system is named the cage guard application. This system uses a DHT 22 sensor which functions to detect changes in temperature and humidity in the cage environment. In addition, this system uses MQ-137 to detect changes in ammonia levels in the cage. The process of storing data using firebase. To facilitate monitoring, this system uses an android application as a monitoring medium for the cage guard system. The coop guard application is also equipped with a camera that functions to see the movements of the chickens in the coop. This is done to observe the behavior of chickens through the camera. The purpose of using the camera is to make sure the chickens are not in a sick condition, which can be seen from whether a chicken is tired when it is in the cage. Based on the test results, this system can send data on the condition of the cage in real time. If this system is compared with similar products that are already on the market, the cost required for using the sensor is lower, resulting in an efficiency of 80.87%. Key Words: Chicken, Breeder, Temperature, Humidity, Amonia, Jaga Kandang

PENINGKATAN EFEKTIFITAS KUALITAS KANDANG AYAM MENGGUNAKAN INTERNET OF THINGS Mia Rosmiati; Trisaputra, M.Riko; Nurul Solihah, Adelia
TEKTRIKA Vol 8 No 1 (2023): TEKTRIKA Vol.8 No.1 2023
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/tektrika.v8i1.5953

Chicken is one of the poultry that is familiar among the public. There are several things that need to be considered when raising chickens. One of them is the condition of the cage. In addition to the conditions of the cage, the influence of temperature, humidity and ammonia gas levels also affect the growth of the chickens. This is quite difficult for breeders who must regularly go to the pen to ensure the temperature, humidity and ammonia gas levels remain at ideal numbers. So, a system was created that can help monitor and control the chicken coop by utilizing Internet of Things (IoT) technology to display information on temperature, humidity, and ammonia gas levels in the chicken coop. This system is named the cage guard application. This system uses a DHT 22 sensor which functions to detect changes in temperature and humidity in the cage environment. In addition, this system uses MQ-137 to detect changes in ammonia levels in the cage. The process of storing data using firebase. To facilitate monitoring, this system uses an android application as a monitoring medium for the cage guard system. The coop guard application is also equipped with a camera that functions to see the movements of the chickens in the coop. This is done to observe the behavior of chickens through the camera. The purpose of using the camera is to make sure the chickens are not in a sick condition, which can be seen from whether a chicken is tired when it is in the cage. Based on the test results, this system can send data on the condition of the cage in real time. If this system is compared with similar products that are already on the market, the cost required for using the sensor is lower, resulting in an efficiency of 80.87%. Key Words: Chicken, Breeder, Temperature, Humidity, Amonia, Jaga Kandang

REMOTE LABORATORY BERBASIS PROTOKOL VIRTUAL NETWORK COMPUTING SEBAGAI MEDIA PEMBELAJARAN JARAK JAUH PROGRAMMABLE LOGIC CONTROLLER Rachman, Isa; Hasin, Muhammad Khoirul; Adhitya, Ryan Yudha; Rahmat, Mohammad Basuki; Adianto, Adianto; Nurcahyo, Agus; Ruwahida, Dewi Rizani
TEKTRIKA Vol 8 No 1 (2023): TEKTRIKA Vol.8 No.1 2023
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/tektrika.v8i1.6044

One effective method that can be applied to online practical learning during the COVID-19 pandemic is remote laboratory which is a combination of the real world and the virtual world using the internet network. This research aims to design remote laboratory based on the Virtual Network Computing (VNC) on Programmable Logic Controller (PLC) which is one of the regular practical devices used in Industrial Automation Laboratory. Remote laboratory in the form of a remote laboratory website for administrators consisting of user management and course management; and for users it consists of login, course and schedule, user order and remote desktop containing PLC Trainer, XG5000 and camera. From the results of remote laboratory testing starting from registration, remote laboratory website, login, course selection, suitability of course schedules, user order and remote desktop can be accessed so that the designed remote laboratory can work properly. The existence of a delay time of 0,52–1,73 seconds for the results of shooting by the camera as a display visualization for online monitoring of practice activities in the laboratory on the client computer is influenced by the condition of the internet network used mainly on server computers. Key Words: practice, online, remote, laboratory, VNC, PLC.

IDENTIFIKASI KARAKTERISTIK MATERIAL DARI BAHAN BATIK TRADISIONAL INDONESIA Ryanu, Harfan Hian; Jumria, Ummi; Siddik, Hawary; Hamsy, Muhammad Daffa; Damayanti, Nabila Rizqa; Fauziah, Regita Nurul; Nugroho, Bambang Setia; Nur, Levy Olivia
TEKTRIKA Vol 8 No 1 (2023): TEKTRIKA Vol.8 No.1 2023
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/tektrika.v8i1.6062

Wearable antenna has an important role in WBAN (Wireless Body Area Network) as the main component that supports on-body communication. This study focuses on the characterization of Material Under Test (MUT) from Indonesian traditional batik material using the CSRR (Complementary split ring resonator) sensor extraction method. The frequency response and magnitude of S21 are used to extract the relative permittivity and loss tangent of the material. From all the responses that appear, a simulation and measurement of wearable antennas is carried out with a working frequency of 2.4. GHz. The antenna with the most similar simulation and measurement results is then selected as a candidate for relative permittivity and loss tangent of the material. From all the 6 frequency responses that emerged from CSRR sensor measurements, the relative permittivity value of 2.083 and the loss tangent of 0.144 achieved a good similarity between the measurement and simulation with an accuracy rate of 99.17%. The final design of the proposed wearable antenna is also validated to transmit heart rate data using the ESP32 microcontroller to the internet using a 2.4 GHz frequency Wifi access point. Key Words: Wearable antenna, extraction of material characteristics, wireless body area network (WBAN), CSRR, material under test, vital signs

ANALISIS PERFORMANSI ALGORITMA SVM, CNN, DAN LSTM UNTUK PENGENALAN KEGIATAN MANUSIA DENGAN URAD FMCW RADAR Ramadhan, Azhar Yunda; De Fitrah, Figo Azzam; Nurhidayat, Muhammad Adi; Suratman, Fiky Yosep; Istiqomah, Istiqomah
TEKTRIKA Vol 8 No 1 (2023): TEKTRIKA Vol.8 No.1 2023
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/tektrika.v8i1.6312

In this study, we compare Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Long ShortTerm Memory (LSTM) algorithms as commonly used machine learning algorithms based on FMCW Radar data for Human Activity Recognition (HAR). The comparison is conducted by evaluating the models on test data and considering the fitting time and the number of parameters required by each model to achieve the desired results, to find the most efficient model that provides the best results. We discovered that the LSTM 01 model with one layer of 16 unit-LSTM produces the best result based on the scoring of several tested models. The model demonstrated an ability to achieve accuracy up to 86% on the test data with a relatively small number of parameters, i.e., 294,725. Key Words: Radar, computation, FMCW, SVM, CNN, LSTM.

PERANCANGAN WEBSITE BERBASIS APLIKASI DENGAN FITUR NOTIFIKASI WHATSAPP UNTUK SISTEM DETEKSI JATUH Nurhidayat, Muhammad Adi; Y. R, Azhar; De Fitrah, Figo Azzam; Suratman, Fiky Y.; Istiqomah, Istiqomah
TEKTRIKA Vol 8 No 2 (2023): TEKTRIKA Vol.8 No.2 2023
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/tektrika.v8i2.6535

This journal discusses the development of a fall detection system using radar as a sensor. The purpose of this system goes beyond technological advancement; it carries significant social impact. It aims to detect fall accidents early and provide prompt intervention to individuals, especially those living alone. In an effort to save lives and reduce the burden on caregivers. The system is connected to an IoT platform and a web-based application that allows users to view real-time detection results. With a notification feature that sends alerts to users and hospitals in the event of a fatal fall accident, this system plays a crucial role in improving the safety and quality of life for those in need. Through testing using the Blackbox Testing method with various scenarios, the system ensures it meets the set requirements and objectives, providing a positive user experience that aligns with expectations, and contributing to ongoing technological development. Key Words: web-based application, fall detection, notifications.

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name
-

Contact Email
-

Phone
-

Journal Mail Official
-

Editorial Address
-

Location
Kota bandung,

Jawa barat

INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name -

Contact Email -

Phone -

Journal Mail Official -

Editorial Address -

Location Kota bandung, Jawa barat INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Contact Name
-

Contact Email
-

Phone
-

Journal Mail Official
-

Editorial Address
-

Location
Kota bandung,

Jawa barat

INDONESIA