MJMahfud Jiono

Mahfud Jiono

*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


Mahfud Jiono has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    6-DoF Pose Estimation Using an End-to-End Pipeline of Neural Network With BP-n-P

    by Mahfud Jiono, Hsien-I Lin, Wen-Hui Chen, Subhajit Nanda

    This paper presents a single-shot, end-to-end deep learning architecture for object detection and 6-DoF pose estimation using an RGB image without post-processing. Previous studies have focused on pose estimation using a two-stage pipeline consisting of a feature extraction network and a pose estimation stage. However, we propose a new network structure that consolidates these two stages into a single-stage architecture to enhance the performance. Our proposed framework involves an end-to-end pipeline that integrates a YOLO architecture with a back-propagating perspective-n-point (BP-n-P) layer to predict the object’s 6-DoF pose directly from an RGB image. The model aims to predict the 2D image coordinates of the corners and center of the 3D tight bounding box around the object in the image. Here, the network back-propagates the pose estimation error through the P-n-P solver to learn the correct object pose. The LineMod dataset, which includes 15,783 RGB images and 13 different object types, was used in the experiment. In the case of single-object pose estimation, we obtained a mean pose accuracy of 71.27% and a mean pixel error of 9.16 pixels without any post-processing or pose refinement. Our approach significantly outperformed other single-shot CNN approaches without refinement conditions such as BB8, SSD-6D, YOLO-6D, PVNet, and GDR-Net. The proposed approach is suitable for robotic manipulation, self-driving cars, and augmented reality.


  • Open Access

    DEVELOPING INTERNET OF THINGS (IOT) TRAINER AS A LEARNING MEDIA FOR REMOTE CONTROL SUBJECT

    by Mahfud Jiono, Fauzy Satrio Wibowo, Muladi Muladi, Siti Sendari, Heru Wahyu Herwanto, Mokh. Sholihul Hadi

    This paper describes the proposed system, which could help the user to understand the basic knowledge of the Internet of Things (IoT) for education purposes. The proposed method has been developed using an all-in-one package trainer of IoT, consisting of several parts, i.e., node sensor, web-based application, node master, and output module. Therefore, three main functions could help the user understand the basic knowledge of IoT: monitoring, data logging, and control functions. Moreover, this proposed system has been developed using System Development Life Cycle (SDLC) method, and it has been validated by material experts and media experts of media kit development. The result shows that the proposed system got a validation score of as much as 95.83% & 97.12% by the experts. Furthermore, the feasibility score from the small group implementation is 91%, while the large group implementation is 93%. Based on the validation and implementation data, it can be concluded that the developed product is feasible to be applied.

  • Detection of Fear of Falls using PPG with Video Stimulation of the Fall Condition

    by Ilham A.E. Zaeni, Mahfud Jiono

    One of the problem of the after stroke walking training is fear of fall. Fear of falling is significantly corresponded to earlier falls and poor physical function. Lower high frequency (HF) power which is measured from heart rate variability has correlation to the stress, panic, anxiety, or worry. This study proposed a method to detect fear of falling using Photoplethysmography (PPG). The PPG signal is acquired using Arduino. The acquired signal is then processed using several step including trend removal, band frequency filtering, band power estimation, and decision system. Trend removal is conducted using moving average while the band frequency filtering is conducted using second order Butterworth band pass filter. The 2 section video is used to induce relax and fear of falling on the subject feeling which is used as the class on decision system. The output of the decision system is then compared to the class and the MAPE is computed. The result shows that the system can yield MAPE 16.63% which is can be categorized as a good result.


  • Object Mapping Estimation on Multi-agent Robot Using Omnidirectional Camera

    by Yogi Dwi Mahandi, Mahfud Jiono, Muladi Muladi, Siti Sendari, Firman Ardiyansyah, Muhammad Rizqi Al-Faiz

    Object detection in a robot vision system is usually used to find out the objects around the robot. In addition, this technique can also be used to recognize the type of object. Beside this, it will generate a position of the object toward the robot and make the robot easier to know the object location and to do its job. However, to position the object in the robot's world model, a mapping process is needed. It requires good precision of object location to generate a good world model map. To do it close to the reality, an estimation can be used. The estimation is the process to predict where the location of an object. One of estimation method in mapping is intersection of two straight line. In this paper, we present the mapping of an object to the robot's world model based on intersection of two straight lines using omnidirectional camera in multi agent robot. It perform well with 6742.87 of MSE and 82.11 of RMSE.

  • Online Motion Planning For Mobile Robot

    by Mahfud Jiono, Yogi Dwi Mahandi, Yuni Rahmawati, Setiadi Cahyono Putro, Firman Ardiyansyah, Dedi Prasetyo

    This paper presents an online motion planning system for mobile robot with a simulator based technique. The simulator is made based on the self-build platform on the mobile robot by using Python language. The collecting data as an information in the simulator is built base on holonomic wheeled type of robot. The specification and configuration of this mobile robot follows the guidelines issued by Middle Sized League Robocup competition. The purpose of this paper to make simulator software as a visualization widget that makes a representation of the coordinate position of the robot and the soccer field condition. The position and orientation of the robot information are gated in this visualization widget. The soccer field representation in a two dimensional condition as a game field of the robot. The robot coordinate as an object with magenta color with have each number of the robot. This object is enable to move in any direction as represent whatever operator want to change the position and orientation of the robot. These condition purpose was used and it can increasing usability of the system. The testing condition between real testing and simulation testing was implemented. Based on the experimental result, the data was conducted we get root mean square error around 1.29 percent of X direction, 1.65 percent of Y direction and around 1.06 percent of the symmetrical trajectory along X and Y coordinate. The result shows that the online motion planning with simulator based can be directly implemented to the soccer robot in the real time condition.


  • Application of Load Shifting Methode Using Pump Storage for Saving Cost Production of Electrical Energy in Java-Bali 500 KV Electrical Power System

    by Langlang Gumilar, Arif Nur Afandi, Muhammad Afnan Habibi, Arya Kusumawardana, Mahfud Jiono, Soraya Norma Mustika

    Electricity energy needs increase every year. If the load continues to increase and the supply of electricity is fixed, then one day it will cause the supply to be smaller than the demand. If electricity provider is able to provide electricity in accordance with the growth of expenses, then there will be an increase in the cost of production of the electric power system as well. Electricity production costs are different every hour, because it follows changes in load curve that changes every hour. This study aims to save electricity production costs for 1 day or 24 hours using load shifting methods with pump storage. The general definition of load shifting method is to move the peak load to the base load, so that the cost of generating electricity at peak loads becomes cheaper. Another way to move peak loads to basic loads can use pump storage. Indonesia has new Cisokan Pump Storage located in West Java. The working principle of pump storage is when the base load will act as pump to move water from the lower reservoir to the upper reservoir, and during this process it will consume electricity. When the peak load will act as generator by draining water from the upper reservoir to the lower reservoir, so that it will reduce electricity consumption during peak loads. In this study, two scenarios will be conducted to determine whether load shifting methods using pump storage can save the cost of production of the electrical power system. The first scenario is the operation of 24-hour electric power system without pump storage. The second scenario is the operation of the electrical power system for 24 hours using pump storage. The result of this study, for scenario 1 the total cost of production for 24 hours is $ 20.251.047,78. For scenario 2, the total production cost for 24 hours is $ 20.174.721,5. From scenario 1 and 2, using pump storage as medium to load shifting methods has proven to save 24 hours of electricity power production costs of $ 76.326,28 and electricity prices are also lower in $/kWh every hour.


  • An Implementation of Multi-object Tracking Using Omnidirectional Camera for Trash Picking Robot

    by Ilham Ari Elbaith Zaeni, Siti Sendari, Dyah Lestari, Yogi Dwi Mahandi, Mahfud Jiono, M. Syaifuddin

    Trash is unwanted materials that are left after someone has used something or things that has been thrown away. It is needed to manage the trash and offers variety of solutions for recycling items that don't belong to trash. Technological development encourages people to working for trash handling and management. The utilization of technology especially in an implementation of the robot technology will help human to handle and manage the trash which includes trash picking, handling, and classifying activities. One of the problems in trash handling using robot is detecting of the trash as an object and determining the distance from the robot to the trash. The main purpose of the implementation of this system is to provide a new method of trash detection using Omnidirectional camera and distance estimation of the object using Euclidean distance estimation method. This experimental design was conducted on four objects with different colors and the distance with the robot. The result shows that trash picking decision will be executed from the nearest distance first. The using Omni-directional camera as the vision system of the robot is work well, although it had some problem to detect and estimate from the object which is caused by the gradation of light and the object has out of the camera range radius.


  • Measuring performance of aerial projection of 3D Hologram Object (3DHO)

    by I. Septiana Asyifa, Jiono Mahfud, Takafumi Matsumaru

    The Aerial Projection of 3D Hologram Object (3DHO) which we have proposed, is a hand gesture-based control system with an interactive 3D hologram object floating in mid-air as the hand movement reference. This system mainly consists of the pyramid-shaped reflector which produces 3D hologram object, the parabolic mirror, and the leap motion controller for capturing hand gesture command. The user can control or interact with 3DHO by using their finger or a baton-shaped object. This paper is focusing on the evaluation of the 3DHO by comparing it to other 3D input devices (such as joystick with a slider, joystick without the slider, and gamepad) on five different positioning tasks. We also investigate the assessment of comfort, ease of learning, and user satisfaction by questionnaire survey. From the experimentation, we learn that 3DHO is not good to use in one-dimensional workspace task, but has a good performance in two-dimensional and three-dimensional workspace tasks. From questionnaire results, we found out that 3DHO is averagely comfortable but may cause some fatigues around arm and shoulder. It is also easy to learn but not satisfying enough to use.


  • Interactive aerial projection of 3D hologram object

    by Jiono Mahfud, Takafumi Matsumaru

    In this paper we present an interactive aerial projection of 3D hologram objects by using the pyramid hologram and parabolic mirror system (for 3D hologram object reconstruction) and the Leap Motion sensor (as a finger movement detector of a user). This system not only can reconstruct and project the 3D hologram object in the mid-air, but also provides a way to interact with it by moving a user's finger. There are three main steps: the reconstruction of 3D object, the projection of 3D hologram object in the mid-air, and the interactive manipulation of 3D hologram object. The first step is realized by using pyramid hologram with LCD display. The second step is achieved with the parabolic mirror hologram. And Leap Motion sensor is used for the last step to detect user finger movement. This paper traces the design concept and confirms the system function of an interactive aerial projection of 3D hologram objects by a prototype demonstration.