Article Per Year (5 Year)
p-Index From 2021 - 2026
4.877
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Jurnal Mahasiswa TEUB Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Widasari, Edita Rosana
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 59 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 59 Documents
Search

 2   3   4   5   6 
Rancang Bangun Sistem Klasifikasi Kualitas Minyak Goreng Dengan Parameter Kecerahan Dan Warna Menggunakan Metode Random Forest Dzakwan Daffa Ramdhana; Fitri Utaminingrum; Edita Rosana Widasari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 6 No 12 (2022): Desember 2022
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Cooking oil is also a raw material that many Indonesians use to cook various types of processed food. Oil has many functions for the human body, including as a source and solvent for vitamins A, E, K, and D, as well as a more effective source of energy when compared to carbohydrates and protein. In society, the oil that is often used is packaged oil and used cooking oil. The use of cooking oil is increasing, causing people to save money by using used cooking oil. The use of oil repeatedly causes quality damage and is very dangerous for human health, one of the diseases is carcinoma, which is cancer cells or malignant tumors of epithelial cells. This happens because oil that is used repeatedly will make peroxide compounds increase in the oil content. The higher the peroxide number, the more concentrated the liquid. There are various ways of testing to determine the quality of oil. First, physical testing methods, one of which is the water content in oil. Then chemically, one of which is the determination of the peroxide number. In addition, physically it can also be seen through the brightness and color of the oil. The system design in this study uses a TCS3200 sensor and a Light Dependant Resistor (LDR) sensor used to measure the color and brightness of the oil respectively. The classification results in the form of less feasible and feasible classes can be seen on the LCD and serial monitor. There are 8 test data from 25 available oil datasets. From the 8 test data, the accuracy of random forest classification is 87.5% and the average computation time is 26.9ms.
Sistem Identifikasi Label Ruangan menggunakan MobileNet SSD dan OCR berbasis Raspberry Pi 3B+ dan Intel Neural Compute Stick 2 Zhuliand Rachman; Fitri Utaminingrum; Edita Rosana Widasari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 6 No 12 (2022): Desember 2022
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

A blind person generally has limitations in visual sensing and uses aids such as a cane to assist their mobility but still has obstacles, especially when they are in a building and want to find the room they are aiming for. Room labels that are usually printed and cannot be recognized by a blind person can be identified with the help of a portable device that performs computing in the field of computer vision. By relying on the MobileNet SSD algorithm, which can detect the presence of room labels with a fast computation, and Optical Character Recognition (OCR) which can recognize the name of the room label, users can hear the name of the room spoken through the speakers. In short, the system converts visual information into audio information that a blind person can receive. Even though the primary processor is an edge device such as the Raspberry Pi 3B+, an additional Intel Neural Compute Stick 2 accelerator device can help the detection process go faster because the detection algorithm involves a computationally intensive deep neural network. Based on the tests carried out in this study, the room label detection test using MobileNet SSD resulted in an accuracy rate of 80% with an average computation time of 68.44 ms. While for recognition using OCR, it produced an accuracy value of 93.65% with an average computation time of 263.05 ms. In addition, the integration results based on digital image input with sound output obtained an accuracy rate of 50% because the sound is only pronounced if the recognition results match the name of the existing room label.
Implementasi Metode Decision Tree untuk Sistem Pendeteksi Stres berdasarkan Detak Jantung dan Kelenjar Keringat Rejeki Puspa Dinasty; Edita Rosana Widasari; Hurriyatul Fitriyah
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 7 No 1 (2023): Januari 2023
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Emotions greatly affect individual behavior and stress refer to physiological responses that occur when individuals fail to respond appropriately to emotional or physical threats. For this reason, it is important to know a person's mental stress, so that further action can be taken, so as not to have a serious impact on physical and mental health. Using the decision tree method with HR and GSR features to detect stres is useful because this method is able to handle data that is not well structured and provides an easily understood visual representation of the decision making process. In addition, HR and GSR features can provide useful information about a person's physical state that can be used to identify stress levels. From the results of system testing with MAX30102 and GSR sensors The accuracy of reading MAX30102 and GSR sensors is seen from the accuracy of the level stress results displayed and the value of the respondent questionnaire results. Stres detection systems through the heart rate and sweat glands have an accuracy of 98.5% while for the average system computing time needed to detect stress of 36802.83 ms or 36.80 seconds. The accuracy results were obtained by testing 24 respondents.
Implementasi Metode K-Nearest Neighbor untuk Sistem Deteksi Covid-19 berdasarkan Suhu Tubuh dan Kadar Oksigen Graciella Fiona Br. Panjaitan; Edita Rosana Widasari; Dahnial Syauqy
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 7 No 1 (2023): Januari 2023
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Covid-19 disease is a contagious disease, so it is necessary to avoid direct contact between humans to minimize exposure to this virus. Examination to the hospital can allow people to be exposed to the Covid-19 virus because direct contact with some people is still carried out in an invasive way. So research is needed to detect the symptoms of Covid-19 non-invasively and does not require a lot of money and time. In this study the detection of body temperature used the MLX90614 sensor by facing the hand towards the front of the sensor so that the body temperature value was obtained. To detect oxygen levels using the MAX30100 sensor by placing your index finger on the sensor then waiting until the oxygen level value is obtained. The two values ​​from the sensor readings will be classified using the K-NN method. The output will be displayed on the LCD in the form of sensor measuring value text and classification results. The test results in this study obtained the accuracy of the sensors used. For measuring body temperature using the MLX90614 sensor, an accuracy of 99.56% was obtained, then for measuring oxygen levels using the MAX30100 sensor, an accuracy of 98.77% was obtained. In the classification test, it is determined by three distances k, namely k=3, k=5, and k=7, where k=3 gets an accuracy of 100%, k=5 gets an accuracy of 90%, and k=7 gets an accuracy of 80%. and from this classification, the average computation time is 2.38 ms.
Sistem Deteksi Hipoksia menggunakan Metode Decision Tree berdasarkan Detak Jantung dan Kadar Oksigen Elisabeth Agustina; Edita Rosana Widasari; Dahnial Syauqy
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 7 No 1 (2023): Januari 2023
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Hypoxia is a condition where there is a continuous lack of oxygen either in the short or long term according to a period. If hypoxia occurs in the short term, what is caused is acute hypoxia. The symptoms found in hypoxia are very fast heartbeat (tachycardia), rapid breathing, dizziness, weakness. Based on the existing problems, the authors want to conduct research to detect hypoxia. The tool designed for this study can detect hypoxia based on heart rate and oxygen saturation. This detection is very easy to use, just by placing your index finger on the MAX30100 infrared sensor, after that you get the measurement results which will be displayed on the LCD screen. The results of these measurements will be the input data for classification. This classification uses the Decision Tree method where this method is very accurate and fast in carrying out the classification process. Classification results will be displayed on the LCD screen. Testing of this tool was carried out 10 trials in detecting heart rate and oxygen saturation. The accuracy obtained when doing the classification is 100%. The MAX30100 sensor when measuring heart rate obtains an accuracy of 97.66% and an error rate of around 2.34. Then, the accuracy obtained when detecting oxygen levels is 98.75% with an error rate of 1.25%
Sistem Deteksi Daun Busuk pada Pakcoy Hidroponik menggunakan Metode Thresholding pada Warna Hue dan Saturasi berbasis Raspberry Pi Rifqi Imam Ramadhan; Hurriyatul Fitriyah; Edita Rosana Widasari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 7 No 2 (2023): Februari 2023
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Agriculture has an important role in Indonesia's economic development as one of the contributors to the state budget which continues to increase every year. In the post-covid 19 pandemic, there were problems that disrupted the economy, impacted on other fields such as agriculture, where the problem of the food crisis would become a problem for Indonesia if it was not handled properly. Agricultural land tends to be increasingly limited because they have to compete for various uses, while people working in agriculture in absolute terms continue to increase causing land ownership to become increasingly narrow. An effective pakcoy planting solution can be planted using hydroponic techniques, so there is a lot of interest from farmers to cultivate pakcoy plants but these plants are susceptible to disease. This research was conducted to detect disease in Pakcoy. The process of detecting Pakcoy disease focuses on knowing the disease of Rotten Pakcoy leaves (Phytoptora sp.) based on the Color Space Hue Saturation Value or HSV. Implementing a simple image using image processing taken using a webcam camera then processed on the Raspberry Pi 4 Model B for detection of pakcoy disease then displayed on the LCD16x2. Based on the research implementation process from start to finish it is able to work as expected. The accuracy of the pakcoy disease detection system resulted in an average accuracy value of 85% for 2 types of classes and an average computation time of 0.001213 seconds for 10 tests.
Klasifikasi Rumah Sehat dengan Metode Jaringan Syaraf Tiruan berbasis ESP32-S Noveriko Noveriko; Dahnial Syauqy; Edita Rosana Widasari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 7 No 2 (2023): Februari 2023
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

A home is a place to return to, rest, and take shelter. Most people spend a large portion of their time at home. The amount of time we spend in our homes makes it important for us to pay attention to the health conditions of our home. A home that is not well-maintained can become a breeding ground for diseases. The solution that I propose is to create a system that can determine a home's health score and also measure the criteria in each room. The system that I have created uses a Artificial Neural Network algorithm and an ESP-32 microcontroller as the processor unit. The system will take in features captured by each sensor, including light intensity (BH1750), air temperature (DHT11), air humidity (DHT11), and carbon monoxide levels in the air (MQ-7). The results of the algorithm and measurements will be displayed on a 20x4 LCD screen, showing the measured features, the obtained score, and the confidence of the classification. The training data used in this system consists of a total of 345 data from 4 classes, with each class consisting of approximately 80 data. The testing was carried out in rooms in a volunteer's home, with a total of 20 rooms. The results of the testing show that 18 were correct and 2 were incorrect, resulting in a system accuracy of 90% with an average computation time of 0.148 seconds.
Sistem Deteksi Kematangan Cabai Hidroponik menggunakan Metode Thresholding pada Warna Hue, Saturation, dan Value Cut Fahrani Dhania; Hurriyatul Fitriyah; Edita Rosana Widasari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 7 No 2 (2023): Februari 2023
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

In the agricultural industry, the main sector in the economic world, digital image processing is needed which aims to increase work productivity and time efficiency to choose the quality of crops to be marketed to the public due to lack of autonomy which results in high production costs and high work costs. Chili is the plant included Solanceae genus that can be implanted in a hydroponic planting system that makes water a substitute for soil media. This hydroponic chili plant uses the Dutch Bucket planting system because it can be used in narrow environments and can be used flexibly. This detection is assisted by a simulator robot that has been designed with a certain height and distance, namely a height of 20 cm and a distance of 30 cm and 20 cm with the help of a Lux Meter to measure the intensity of ambient light which is then designed using Qt Designer as a Graphical User Interface platform which will display the results of hydroponic chili detection through the bounding box. The accuracy value on the successful detection of hydroponic chili maturity resulted in a percentage of 93% and a computational mean value of 3.841 seconds.
Implementasi Robot Manipulator menggunakan Sinyal Electromyography berdasarkan Pergerakan Kaki Manusia Andre Adikusuma; Edita Rosana Widasari; Eko Setiawan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 7 No 2 (2023): Februari 2023
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Technological developments in the medical field have developed rapidly, one example is the manipulator robot. For example, in some cases there are people suffering from stroke who have difficulty moving their limbs. Due to the limited number of rehabilitators, the rehabilitation process took longer and they had to wait in line to carry out rehabilitation. The movement of the robotic manipulator's leg will be based on the movement of the human leg by reading electromyography (EMG) signals generated from the leg muscles through the electrodes. Then an exponential filter is used to reduce the noise from the EMG signal. After filtering the signal obtained will be classified using a decision tree classification. Then the AX-12A servo is used to move the legs of the manipulator robot which has 4 degrees of freedom. The results of the decision tree classification have amplitude values for each movement, which include 0V to 1.995V as a squatting movement with an angle of 450; 1.995V to 2.985V as a 90° seated motion; 2.985V to 5V as a standing movement with an angle of 1800. The test results obtained determine the movement of the leg robot has an accuracy of 70.667% for the total average accuracy. The subjects used were 10 with 5 movements at each angle.
Sistem Deteksi Insomnia berbasis Elektrokardiogram menggunakan Fitur Mean RR dan Standar Deviasi NN dengan Metode K-Nearest Neighbours M. Yunior Dwi Ashari; Edita Rosana Widasari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 7 No 2 (2023): Februari 2023
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Insomnia is a sleeping sickness in which the time and quality of human sleep is not sufficient due to difficulty getting to sleep or difficulty maintaining sleep. Early diagnosis and treatment of insomnia is necessary to prevent chronicity and death resulting from untreated insomnia. The body's required ECG signal can be detected by installing a sensor on the human body. The ECG signal has several points, namely P, Q, R, S and T points. There are PR intervals, PR segments, QRS complex, ST segments, and QT intervals as areas in the ECG signal. In this study, we will use the R-R interval of human ECG signals taken when the sleep condition is for 2 hours which already represents one person's sleep cycle. The features to be used are the Mean RR and SDNN features. The K-Nearest Neighbours method classifies new data by finding the shortest distance from the training data, this makes this method suitable for this study because the training data used has significant differences between one class and another class. The tools that will be used to detect insomnia are the Arduino Uno microcontroller and the AD8232 module which are used to detect and filter the detected signals. AD8232 is a module used to acquire ECG signals. The use of K-Nearest Neighbours as a classification method has an accuracy of 86% for K = 3 and obtain an average computation time of 79.9 ms.
Co-Authors Achmad Ghifari Adharul Muttaqin Adhitya Bhawiyuga Agung Setia Budi Ahmad Haris Wahyudi Andhika Nino Pratama Andre Adikusuma Andrika Wahyu Wicaksono Andy Hartono Anethasia Putri Prasetyowati Angger Dimas Bayu Sadewo Ariyan Jazmi Aulia Zhafran Auliya Firdaus Barlian Henryanu Prasetio Barlian Henryranu Prasetio Batara Dolly Nababan Cut Fahrani Dhania Dahnial Syauqy Denis Reza Ramdani Desy Marinda Oktavia Sitinjak Dody Kristian Manalu Dwinanda Romolo Dzakwan Daffa Ramdhana Eko Setiawan Elisabeth Agustina Fathul Abdillah Khosin Fatkhurrozi Fatkhurrozi Fitriyah, Hurriyatul Graciella Fiona Br. Panjaitan Hafid Ilmanu Romadhoni Harry Mulya Henry Trenggana Hery Julianto Situmorang Izzati Firsta Wijayanti M. Yunior Dwi Ashari Moch Rizki Cahyadi Mochammad Hannats Hanafi Ichsan Mohammad Fauzin Amin Mohammad Hafidh Wildan Maulana Muhamad Fauzan Alfiandi Muhammad Ammar Hassan Muhammad Fadhil Sadeli Muhammad Fauzan Edy Purnomo Muhammad Nur Arssy Muhammad Risyat Nashrullah Muhlis Agung Saputro Noveriko Noveriko Nur Syifa Syafaat Onky Soerya Nugroho Utomo Putri Laras Rinjani Qonita Luthfiyani Rakhmadhany Primananda Rejeki Puspa Dinasty Reza Hastuti Rifki Pinto Hidayat Rifqi Imam Ramadhan Rizal Maulana Rosa Mulyanis Chan Sabriansyah Rizqika Akbar Salsabila Salsabila Sasmita Eko Raharjo Selina Kusmiawati Syifa' Hukma Shabiyya Thomas Oddy Chrisdwianto Tri Oktavia Mayasari Utaminingrum, Fitri Zhafran Wadiansyah Zhuliand Rachman Zonnete Bryllian Dheo