Electronics Engineering Polytechnic Institute of Surabaya

Surabaya, Indonesia

Electronics Engineering Polytechnic Institute of Surabaya

Surabaya, Indonesia

Time filter

Source Type

Wicaksono H.,Petra Christian University | Khoswanto H.,Petra Christian University | Kuswadi S.,Electronics Engineering Polytechnic Institute of Surabaya
Telkomnika | Year: 2011

Behaviors coordination is one of keypoints in behavior based robotics. Subsumption architecture and motor schema are example of their methods. In order to study their characteristics, experiments in physical robot are needed to be done. It can be concluded from experiment result that the first method gives quick, robust but non smooth response. Meanwhile the latter gives slower but smoother response and it is tending to reach target faster. Learning behavior improve robot's performance in handling uncertainty. Q learning is popular reinforcement learning method that has been used in robot learning because it is simple, convergent and off policy. The learning rate of Q affects robot's performance in learning phase. Q learning algorithm is implemented in subsumption architecture of physical robot. As the result, robot succeeds to do autonomous navigation task although it has some limitations in relation with sensor placement and characteristic. © 2011 Universitas Ahmad Dahlan. All rights reserved.


Sumantri B.,Electronics Engineering Polytechnic Institute of Surabaya | Sumantri B.,Toyohashi University of Technology | Uchiyama N.,Toyohashi University of Technology | Sano S.,Toyohashi University of Technology
2013 IEEE/SICE International Symposium on System Integration, SII 2013 | Year: 2013

In this paper, we design a least square based sliding mode control to solve the over determined problem in translation motion of a quad-rotor helicopter while in rotational motion we employ a regular sliding mode control. A saturation function is designed around a boundary layer to reduce the chattering phenomenon that occurs in a sliding mode control. The dynamics of the quad-rotor helicopter is derived by the Newton-Euler formulation for a rigid body. A constant plus proportional reaching law is utilized to increase reaching rate of the sliding mode controller. The stability of the proposed algorithm is evaluated on the basis of Lyapunov stability theory. Experimental results under wind disturbance are presented to show the robustness and effectiveness of the proposed control algorithm. © 2013 IEEE.


Sumantri B.,Toyohashi University of Technology | Sumantri B.,Electronics Engineering Polytechnic Institute of Surabaya | Uchiyama N.,Toyohashi University of Technology | Sano S.,Toyohashi University of Technology
Mechanical Systems and Signal Processing | Year: 2016

In this paper, a new control structure for a quad-rotor helicopter that employs the least squares method is introduced. This proposed algorithm solves the overdetermined problem of the control input for the translational motion of a quad-rotor helicopter. The algorithm allows all six degrees of freedom to be considered to calculate the control input. The sliding mode controller is applied to achieve robust tracking and stabilization. A saturation function is designed around a boundary layer to reduce the chattering phenomenon that is a common problem in sliding mode control. In order to improve the tracking performance, an integral sliding surface is designed. An energy saving effect because of chattering reduction is also evaluated. First, the dynamics of the quad-rotor helicopter is derived by the Newton-Euler formulation for a rigid body. Second, a constant plus proportional reaching law is introduced to increase the reaching rate of the sliding mode controller. Global stability of the proposed control strategy is guaranteed based on the Lyapunov's stability theory. Finally, the robustness and effectiveness of the proposed control system are demonstrated experimentally under wind gusts, and are compared with a regular sliding mode controller, a proportional-differential controller, and a proportional-integral-differential controller. © 2015 Elsevier Ltd. All rights reserved.


Walter C.,Vienna University of Technology | Syafrudin M.,Vienna University of Technology | Syafrudin M.,Electronics Engineering Polytechnic Institute of Surabaya | Schweinzer H.,Vienna University of Technology
ISPRS International Journal of Geo-Information | Year: 2013

There are many situations in which it is desirable to use a Local Positioning System (LPS), which constitutes a complete and independent unit, offers high accuracy and in addition is economical to realize. This paper describes the LPS LOSNUS (Localization of Sensor Nodes by Ultra Sound). LOSNUS is a complete and independent LPS where the same system can be used for localization and calibration. Primarily designed for locating numerous quasi-static devices, special care of system construction has taken on costly factors, especially in the construction of the infrastructure and of sensor nodes where locating can be realized with minimal additional hardware costs. LOSNUS enables a calibration process without the need of additional expensive tools and/or laborious time in order to get accurate positions of transmitters. As a result, LOSNUS delivers high locating accuracy at medium update rates, and in case of sufficient number of transmitters can also tolerate single failures in the Time of Arrival (ToA) measurement, allowing arbitrary failure modes. In this article, the system is presented starting from design, realization and algorithms of localization and calibration. Finally, new measurement results are showing the high accuracy of localization based on a discussion of the applied uncertainty description. © 2013 by the authors; licensee MDPI, Basel, Switzerland.


Alasiry A.H.,Electronics Engineering Polytechnic Institute of Surabaya | Ohyama S.,Tokyo Institute of Technology
Sensors and Transducers | Year: 2011

In centralized range-based localization techniques, sufficiency of inter-node range information received by the base station strongly affects node position estimation results. Successful data aggregation is influenced by link stability of each connection of routes, especially in a multi-hop topology model. In general, measuring the inter-node range is only performed for position determination purposes. This research introduces the use of inter-node range measurement information for link selection in a multi-hop route composition in order to increase the rate of data aggregation. Due to irregularity problems of wireless media, two areas of node communication have been considered. The regular communication area is the area in which other nodes are able to perform symmetrical communication to the node without failure. The irregular area is the area in which other nodes are seldom able to communicate. Due to its instability, some existing methods tried to avoid the irregular area completely. The proposed method, named Virtual Boundaries (VBs) prioritizes these areas. The regular communication area's nodes have high priority to be selected as link vertices; however, when there is no link candidate inside this area, nodes within the irregular area will be selected with respect to their range to the parent node. This technique resulted in a more robust multihop topology that can reduce isolated node numbers and increase the percentage of data collected by the base station accordingly. © 2011 IFSA.


Alasiry A.H.,Electronics Engineering Polytechnic Institute of Surabaya | Ohyama S.,Tokyo Institute of Technology
2012 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2012 - Proceedings | Year: 2012

In centralized range-based localization techniques, sufficiency of inter-node range information collected by the base station strongly affects node position estimation results. In an evenly distributed network, which every node can accurately measure ranges each other, it is easy to calculate every node position using range-based, since there be only one possibility of local minimum. Unfortunately, in real flooded nodes deployment WSNs, it is difficult to find the uniformity. The density of network will be varying from part to part. Nodes sparse in low density part will potentially have insufficient or even none range information. In such condition, localization program will find more than one possibilities of local minimum, the range based localization program will have difficulties to resolve nodes positions, and further, it also influences entire nodes localization. Therefore, this research proposed a new approach in overcoming sparse condition by utilizing non-range information as tool to verify whether a local minimum occurred is correct. This technique resulted in a more successful localization in sparse distributed WSNs. © 2012 Universitas Indonesia.


Rahadianto H.,Electronics Engineering Polytechnic Institute of Surabaya | Fariza A.,Electronics Engineering Polytechnic Institute of Surabaya | Hasim J.A.N.,Electronics Engineering Polytechnic Institute of Surabaya
Proceedings of 2015 International Conference on Data and Software Engineering, ICODSE 2015 | Year: 2015

Indonesia has the geographical conditions which are particularly vulnerable to disasters, especially floods and climate change. Throughout Indonesia, it is recorded that there are 5,590 main rivers and 600 rivers have the potential to cause flooding among others. One of it is Bengawan Solo River, which is the longest river in Java. The floods that hit the area have resulted in disruption of public health, disrupted economic activity, and damaged urban infrastructure. The phenomenon of floods and their negative impacts in the area of the Bengawan Solo river banks, indicating a condition of the area and the public about the lack of understanding of the characteristics of the hazards, behaviours that lead to degradation of natural resources, and lack of early warning that causes unpreparedness and inability in the face of danger. The purpose of this project is to be able to create an information system that can provide an assessment of the risk management in the Bengawan Solo's flood prone areas that passed in the province of East Java, by building a web-based information system that includes information on threats, vulnerabilities, and capacities, summarized in the disaster risks analysis that integrated with Geographic Information System to provide mapping areas that have high levels of risk in accordance. Based on the factors that are already said above and calculated by Analytical Hierarchy Process, the result of this project is a map with marked regions divided into three levels of risk like High, Medium, and Low using Natural Breaks to divide it. It also, by providing the risk-level for the regions, help the system to assess how much impact and damage that will be hit the risky area and give the recommendation to government and people how to increase the preparedness so it can reduce the damage from flood. © 2015 IEEE.


Rokhana R.,Electronics Engineering Polytechnic Institute of Surabaya | Anggraini S.,Electronics Engineering Polytechnic Institute of Surabaya
Proceedings - 2015 International Electronics Symposium: Emerging Technology in Electronic and Information, IES 2015 | Year: 2015

Tomography is a method that can reconstruct the internal image of a non-invasively object, based on the measurements. On acoustic tomography, measured data is obtained from the output of ultrasonic transducer that is passed to the object. Velocity of waves that pass through the object is processed to obtain the impulse response and sampling projection. Once processed by the FFT, both these quantities is filtered by the back projection filter to obtain image reconstruction. This method that conducted to the air, water, mud, aluminum, and the combination of those materials, will showed gradations of color in the image in the form of a mesh, contour, pcolor, and surface. This shows the velocity difference when the ultrasonic wave reflected or transmitted by the material of measured object that can be indicated as the difference in the substance of the material in the measured object. © 2015 IEEE.


Setyadi A.D.,Electronics Engineering Polytechnic Institute of Surabaya | Harsono T.,Electronics Engineering Polytechnic Institute of Surabaya | Wasista S.,Electronics Engineering Polytechnic Institute of Surabaya
Proceedings - 2015 International Electronics Symposium: Emerging Technology in Electronic and Information, IES 2015 | Year: 2015

In the psychology, there are four fundamental personality types of human: sanguine, choleric, melancholic, and phlegmatic. One way to know the human fundamental personality is based on test, and one kind of test is Grapho test (handwriting test). In this study has been conducted detection of the human fundamental personality using combination of some face features: the eyes, lips, and nose (without test). Those features are obtained from facial image. Distance between two corners of the eyes, high of eyes, ratio of the mouth width and nose, the width ratio of two eyes, and thickness of lower lip have been used as feature extractions. By using artificial neural network (backpropagation) and based on such feature extractions, the fundamental personality is detected. Related to the experimental results, system can detect the human fundamental personality for the same input image data with training average 85.5%. The identification result for the different input image data with training is average 42.5%, this condition occurred caused by identification of personality for choleric and phlegmatic was less than 50%. © 2015 IEEE.


Sulistijono I.A.,Electronics Engineering Polytechnic Institute of Surabaya | Baiqunni H.H.,PT Indonesia Epson Industry | Darojah Z.,Electronics Engineering Polytechnic Institute of Surabaya | Purnomo D.S.,Electronics Engineering Polytechnic Institute of Surabaya
IEEE International Conference on Fuzzy Systems | Year: 2014

In this research, we propose a system of vowel recognition on the shape of the lips using a neural network backpropagation. For recognizing the shape of the vowels in the lips by image capturing through the webcam, and then processed through image processing which includes edge detection, filtering, mouth feature extraction, integral projection and vowels recognition on the lips using a back propagation neural network. The vowel recognition results obtained at the lips of the testing process neural network based on the training data and test data. The proposed method works well. The final results obtained from this research is a system that able to detect the lips with good features, with the success of recognizing vowels using 250 training data is 70%. The output data from the vowel recognition on the lips is used as an input to Lipsynchrobot that followed the gesture of human lips. © 2014 IEEE.

Loading Electronics Engineering Polytechnic Institute of Surabaya collaborators
Loading Electronics Engineering Polytechnic Institute of Surabaya collaborators