RWRomy Budhi Widodo

Romy Budhi Widodo

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Romy Budhi Widodo has a total of 52 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Studi Klasifikasi Gerakan Semaphore menggunakan Fuzzy Mamdani dari Data IMU Sensor

    by Tobias Nagata Budimartono, Romy Budhi Widodo

    Sering dijumpai di komunikasi antar kapal dan dikepramukaan penggunaan bendera semaphore untuk media komunikasi jarak jauh. Pembelajaran semaphore umumnya dilakukan secara manual dan menggunakan pendeteksian dengan citra digital. Namun keduanya memiliki keterbatasan yaitu ketersediaan tenaga ahli/tutor dan permasalahan pencahayaan. Mengingat pentingnya semaphore untuk komunikasi jarak jauh maka ahli semaphore memerlukan guidance system yang dapat menilai gerakan latihan. Penelitian ini menggunakan fuzzy logic dengan mamdani inference system. Metode yang digunakan adalah memasang sensor inersial pada kedua pergelangan tangan untuk mendapatkan data sudut gerakan tangan. Sensor inersial yang digunakan menghasilkan tiga sudut orientasi yaitu roll, pitch, dan yaw; namun dalam penelitian ini digunakan sudut roll. Gerakan semaphore pada penelitian ini berporos hanya pada satu sumbu sehingga data sudut roll yang digunakan untuk analisis. Sensor inersial secara nirkabel memberikan data ke komputer yang telah berisi perangkat lunak fuzzy system. Pada dasarnya gerakan semaphore memiliki delapan titik sudut, namun dalam penelitian ini telah ditemukan metode baru menggunakan lima area untuk mengelompokkan sudut kedua tangan. Pengelompokan pada lima area bermanfaat untuk penciptaan rule fuzzy. Output fuzzy berupa skor sesuai atau tidak sesuai. Eksperimen menggunakan lima orang subjek yang diminta melakukan delapan karakter yang mewakili huruf A-Z, dan spasi. Hasil pengujian menunjukkan sistem berhasil mendeteksi gerakan dengan akurasi 67.5%. Hasil umpan balik analisis menunjukkan bahwa kedepannya diperlukan sebuah sensor yang dapat mendeteksi kemiringan torso untuk mengkompensasi postur tubuh yang kurang tegak saat subjek melakukan eksperimen.

  • Study of EMG-based Mouse Clicks Type Detection

    by Romy Budhi Widodo, Devina Trixie, Windra Swastika

    The operation of a computer required humans to use several parts of their body. However, there were some conditions where humans cannot operate computers correctly or in a normal position; examples of these conditions were accident victims and people with disabilities. Therefore, a system was needed to help make it easier for these people to operate the computer. This study developed a system that can classify click types using EMG sensors, the K-NN method, and the SVM method. EMG sensors helped take data in the form of signals from human muscle contractions which will later be classified into left-click and right-click. At the same time, it was useful for classifying these types of clicks for the K-NN and SVM methods. Data from EMG sensors were trained using the K-NN and SVM methods using 54 data sets in each class, namely left-click and right-click classes. The K-NN method was trained using k=3, 5, 7, 9, and 11. The SVM method used linear kernels, Radial Basis Function (RBF), polynomials, and sigmoids. After that, the accuracy values of the two methods will be compared. The study has successfully classified the types of clicks based on the input from the EMG sensor using the K-NN method with the highest accuracy results using k=3, which was 81.81%, and the SVM method using polynomial kernels which were 84.84%. The highest accuracy value was obtained by comparing the two methods, namely using the polynomial kernel SVM method. Adding datasets and conducting experiments using other methods as further comparisons can be used to improve system accuracy.

  • Open Access

    CNN Based Transfer Learning for Malaria Parasite Detection Using Thin-Blood Smear Images

    by Windra Swastika, Benedictus Julian Pradana, Romy Budhi Widodo, Rehmadanta Sitepu, Gregorius Guntur Sunardi Putra

    Transfer learning has been used in computer vision research, including in the health sector. In the health sector, the input image is generally an x-ray image or a microscopic image. In this study, transfer learning for models that have been trained using CNN to detect malaria parasites in red blood cell images. The deep CNN pre-trained model uses 3 architectures, namely ResNet50V2, EfficientNetB0, and InceptionV3. For each architecture, experiments will be carried out and compare which architecture is better in detecting malaria parasites. Based on experiments conducted without fine tune, the accuracy ranges from 0.76 – 0.81 for ResNet50v2, 0.76 – 0.80 for EfficientNetB0, and 0.77 – 0.82 for InceptionV3. The dataset is a collection of Blood Smear images which have two classes, uninfected and parasitized. The total number of datasets is 27,558, which is divided into two classes with the same number of different image sizes.


  • Open Access

    Rancang Bangun Prototipe Sistem Pemantauan dan Pemetaan Lampu Penerangan Jalan Umum (PJU) Berbasis Arduino UNO

    by Aleksander Bima Tansri, Mochamad Subianto, Romy Budhi Widodo, Yusuf Giovanno, Octaviani Intan Randi

    Public road lighting (PRL) is a facility used by the community to work at night. Dinas Perumahan dan Permukiman (DISPERKIM) department is a tasked with making improvements and regulating PRL. However, DISPERKIM officers are still experiencing delays in making PRL improvements, because PRL monitoring and regulation is still by visiting each PRL location. The experimental results show, the trial of sending data with 100 experimental from GSM Shield SIM900 gets 1.55 seconds, while the NRF24L01 device is 1.69 seconds. Based on the results of trials on sending data shows the delay of sending data for the prototype parent by 50.7 seconds, and 56.4 seconds. Whereas the testing delay of sending data for child prototypes was 147.8 seconds or 02:27 minutes, and by 143.5 seconds or 02:23 minutes. The function of experimental is helping officer (DISPERKIM) to get a data for calculation and prediction about PJU condition on every area. Based on the design of the test system can be stated to run well, because the system can do remote monitoring and mapping.


  • Open Access

    Peningkatan Efisiensi Kerja Guru Melalui Pembuatan Aplikasi Rapor Berbasis Komputer

    by Romy Budhi Widodo, Mochamad Subianto, Grace Imelda

    The domain of the activity is technology for the society whereas the focus is practical computer science for the society. The background of our activity is based on the needs of YPK junior high school in Malang city, Indonesia. The school need to develop computer-based school report card and also daily grade card for teachers. The method for software/application development is spiral model which consist of the cycle of system identification, risk analysis, and enhancement of the prototype to be an operational prototype. Evaluation of the product was based on the Computer System Usability Questionnaire (CSUQ) from IBM. The CSUQ using 5 scale of Likert scale contains three categories: 1) system usefulness (SYSUSE), 2) information quality (INFOQUAL), and 3) interface quality (INTERQUAL). The mean rank’s result in order from the greatest to the lowest is SYSUSE, INTERQUAL, and INFOQUAL, respectively. It was reported that SYSUSE category was superior to INFOQUAL (U = 3369.5, p = 0.0005). Overall, the user satisfaction score is 78.4%, which is in the “worthy” category


  • The IMU and Bend Sensor as a Pointing Device and Click Method

    by Romy Budhi Widodo, Agustinus Bohaswara Haryasena, Hendry Setiawan, Mochamad Subianto, Paulus Lucky Tirma Irawan, Ari Yudha Lusiandri, Didik Dwi Suharso, Ardiansyah, Iskandar

    A pointing device is one of the important interfaces between human and computer. A mouse is usually used as a pointing device; however, people with physical impairments who can not use a mouse due to its operation should use a table. One candidate for solving this problem is using an upper-arm movement combined with an inertial measurement unit sensor. The upper-arm gestures would be mapped and used to manipulate the mouse cursor on the monitor display. The ‘clicking’ action will be accomplished using a bending sensor attached on the opposite upper-arm. This study evaluates the combination of the IMU and bend sensor (IMU+Bend) as a substitute for the mouse. The evaluation is based on ISO/TS 9241-411: Ergonomics of human-system standard. The results mentioned that the use of IMU is a promising way to emulate the movement of cursor. However, the usage of bend sensor is uncomfortable when it is used as a clicking method. The throughput of the proposed is 1.75 bps, and qualitative results show that the mean of comfort is 4.85 on a Likert scale ranged from 1 to 7.


  • Open Access

    Implementation of Backpropagation Neural Network and Extreme Learning Machine of pH Neutralization Prototype

    by Imam Sutrisno, Muhammad Firmansyah, Romy Budhi Widodo, Ardiansyah Ardiansyah, Mohammad Basuki Rahmat, Achmad Syahid, Catur Rakhmad Handoko, Agus Dwi Santoso, Ari Wibawa Budi Santosa, Riries Rulaningtyas, et al.

    This paper presents a comparison between Backpropagation Neural Network and Extreme Learning Machine for pH neutralization process. The system has one input variable and two output variables. The input is pH value in neutralization container and the outputs are time on solenoid valve of acid solution and time on solenoid valve of base solution. There is a sequence system in pH neutralization process to regulate the flow of liquids under certain conditions, so that the liquid does not exceed the maximum capacity if the pH has not reached the setpoint. The performance analysis is done for Backpropagation Neural Network and Extreme Learning Machine implementation in neural region by keeping setpoint 7. From the implementation result, it is found that Backpropagation Neural Network gives better result when compared with Extreme Learning Machine for pH neutralization prototype.


  • Open Access

    Grasping and Attached Mode in Human-Computer Interaction in the Study of Mouse Substitution

    by R B Widodo, R M Quita, S Amrizal, R S Gunawan, C Wada, A Ardiansyah, I Sutrisno, M B Rahmat, A Z Arfianto, C R Handoko, et al.

    Some disabilities caused by sensory malfunction, accident, or congenital disorder could cause people difficulty in grasping the computer mouse. A well-known substitute uses an inertial sensor to monitor the body's orientation. This paper evaluates the efficiency and effectiveness of different methods of holding the sensor. There are two modes of holding the sensor, the grasping mode and the attached mode; we also evaluate a mouse as a baseline. The attached mode works by placing the sensor on the back of user's hand. The quantitative and qualitative evaluation procedure is based on ISO/TS 9241 part 411: Ergonomics of human-system interaction standard. The test consists of four levels of difficulty and indicates that the throughput and task completion times were not statistically different between grasping and attached mode. We also found that grasping mode and attached mode did not show significantly statistical differences in comfort and fatigue based on the questionnaires. The results also suggest that the orientation of the hand used in grasping and attached modes is suitable only for lower-impact computer use.


  • Open Access

    A study of hand-movement gestures to substitute for mouse-cursor placement using an inertial sensor

    by Romy Budhi Widodo, Reyna Marsya Quita, Rhesdyan Setiawan, Chikamune Wada

    This paper examines the new study of hand orientation as a substitute for computer-mouse movement and is evaluated based on ISO/TS 9241 part 411: Ergonomics of human–system interaction-evaluation methods for the design of physical input devices. Two pairs of hand-orientation candidates were evaluated, using, for example, pitch–roll and pitch–yaw to substitute for up–down and left–right mouse-cursor movements. The up–down cursor movement was generated from the pitch orientation, while the left–right cursor movement was generated from the roll or yaw orientation, depending on the evaluation of the proposed gesture. The research employed a standard computer mouse as a baseline comparison for the study. The empirical study was conducted to evaluate quantitative performance such as throughput and movement time. The best impression resulted when the throughput had the greatest value as well as the shortest movement time. The performance test was based on Fitts's law using a multi-directional tapping test as suggested by ISO/TS 9241-411. The test was divided into several levels of difficulty, including high, medium, low, and very low. The other assessment is qualitative and was performed using the comfort-rating scale questionnaire and rating of perceived exertion of comfortability and fatigue. The quantitative results show that pitch–yaw throughput is slightly higher than for the pitch–roll gesture, and that the movement time in pitch–yaw is slightly less than in pitch–roll, although there is no statistically significant difference between the two. We also found that pitch–yaw movements have a higher level of comfort based on the comfort-rating scale test. Since the test was divided into levels of difficulty, we identified those gestures suitable for the task with a low and very low level of difficulty based on throughput, movement time, and error-rate results. Finally, this study suggests that pitch–roll and pitch–yaw movements of the hand can be used as substitutes for the mouse, and that pitch–yaw movements are superior in regard to causing less fatigue than pitch–roll movements. Furthermore, this study provides a new suggestion for a suitable level of difficulty when using an inertial sensor as an emulator for the movement of a mouse cursor in the field of human–computer interaction.


  • Study of the Android and ANN-based Upper-arm Mouse

    by Hartawan Sugihono, Romy Budhi Widodo, Oesman Hendra Kelana

    Disability is a person's condition in the physical, intellectual, mental, and/or sensory limitations in the long term. This study is reserved for those who do not have the lower arm in order to operate the computer normally. This study uses orientation sensor on the smartphone as the main sensor to move the cursor and click. Delivery of data from smartphone to computer is using Bluetooth. This study will compare two gestures from a combination of orientation sensors on the upper arm: gesture 1 using pitch-yaw motion and gesture 2 using pitch-roll motion; to move the cursor on the monitor. Left-click and right-click using ANN is to detect upper arm jerk movements. Evaluation using ISO/TS 9241-411 standard: ergonomics of human-system interaction; which includes performance evaluation and comfort of the gesture. Performance results of throughput, movement time, comfort and fatigue between gestures were not significantly different between those gestures. The result of the effort questionnaire is that gesture 1 has the highest effort on the shoulder and gesture 2 has the highest effort on the hand.