Articles
9,226 Documents
Building student’s performance decision tree classifier using boosting algorithm
Farid Jauhari;
Ahmad Afif Supianto
Indonesian Journal of Electrical Engineering and Computer Science Vol 14, No 3: June 2019
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v14.i3.pp1298-1304
Student’s performance is the most important value of the educational institutes for their competitiveness. In order to improve the value, they need to predict student’s performance, so they can give special treatment to the student that predicted as low performer. In this paper, we propose 3 boosting algorithms (C5.0, adaBoost.M1, and adaBoost.SAMME) to build the classifier for predicting student’s performance. This research used 1UCI student performance datasets. There are 3 scenarios of evaluation, the first scenario was employ 10-fold cross-validation to compare performance of boosting algorithms. The result of first scenario showed that adaBoost.SAMME and adaBoost.M1 outperform baseline method in binary classification. The second scenario was used to evaluate boosting algorithms under different number of training data. On the second scenario, adaBoost.M1 was outperformed another boosting algorithms and baseline method on the binary classification. As third scenario, we build models from one subject dataset and test using onother subject dataset. The third scenario results indicate that it can build prediction model using one subject to predict another subject.
Analysis of substrateintegrated frequency selective surface antenna for IoT applications
Govardhani Immadi;
M. Venkata Narayana;
A. Navya;
C. Anudeep Varma;
A. Abhishek Reddy;
A. Manisai Deepika;
K. Kavya
Indonesian Journal of Electrical Engineering and Computer Science Vol 18, No 2: May 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v18.i2.pp875-881
Antennas are long used for communication of data since a century and their usage has been diversified over the past two decades and the antennas also entered the domain of medical fields. A rectangular microstrip patch antenna has been designed on a substrate integrated waveguide with frequency selective surface which is in the shape of a square. The design of this antenna with SIW are done by using CST on a low cost FR4 substrate where єr =4.4, h=1.58 mm and tan δ=0.0035. The SIW structure merit is utilized on the traditional FSS is simulated and verified by using CST.
Swarm Intelligence for Perception Layer Design of Internet of Things
Chuanyun Wang;
Enyan Sun;
Feng Tian;
Na Lin
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: January 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Internet of Things is the extension and expansion of Internet from the virtual world to the real world, in which a large number of resource-constrained devices are used to collaborative perception, and it identifies objects and gathers information in the case of no centralized control, no global model. However, the swarm intelligence can take advantage of many simple autonomous individuals to exhibit complex emergent behaviors. In this paper, the characteristics and commonality of perception layer and swarm intelligence were analyzed firstly, and then the architecture of smart individual, self-organization modeling, swarm behavior emergence pattern were analyzed and designed. Finally, intelligentization for perception layer was achieved on the support of middleware. DOI : http://dx.doi.org/10.11591/telkomnika.v12i1.4149
Model Construction and Simulation of Weighted Industrial Cluster Complex Network
Lijun Wang;
Lei Wen
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 10: October 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v12.i10.pp7330-7336
In this paper, we construct a weighted industrial cluster complex network model according to preferential attachment and local world mechanism, in which the logistics amount of business contact between one enterprise and others is defined as edge weight. We simulate and analyze statistic characteristics of the industrial cluster model such as degree distribution, point strength, point strength-point strength correlation, and relationship with degree and point strength. The simulation results show that the degree and point strength distribution are accord with power law distribution, the point strength-point strength correlation is negative, and the relationship with degree and point strength is strongly linear.
A New Approach of Detection Algorithm for Reducing Computation Complexity of MIMO systems
Mohammed Qasim Sulttan
Indonesian Journal of Electrical Engineering and Computer Science Vol 1, No 1: January 2016
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v1.i1.pp159-167
Multiple-Input Multiple-Output (MIMO) technique is a key technology to strengthen and achieve high-speed and high-throughput wireless communications. . In recent years, it was observed that frequent detecting techniques could improve the performance (e.g., symbol error rate ‘SER’) of different modern digital communication systems. But these systems faced a problem of high complexity for the practical implementation. To solve the problem of high complexity, this work proposed Frequent Improve K-best Sphere Decoding (FIKSD) algorithm with stopping rule depending on the Manhattan metric. Manhattan metric is proposed to use with FIKSD in order to achieve the lowest complexity. FIKSD is a powerful tool to achieve a high performance close to the maximum likelihood (ML), with less complexity. The simulation results show a good reduction in computation complexity with a cost of slight performance degradation within 1dB; the proposed FIKSD requires 0% to 94% and 82% to 97% less complexity than Improved K-best Sphere Decoder (IKSD) and K-best Sphere Decoder (KSD) respectively. This makes the algorithm more suitable for implementation in wireless communication systems.
A Novel Unit Power Factor Rectifier Based on Three-phase Digital PLL
Xuegui Zhu;
Zhihong Fu;
Xiangfeng Su
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 7: July 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
A novel three-phase phase-locked loop solution is proposed based on D-Q transformation aiming at the AC-DC rectifier with high efficiency and high power factor. The phase-locked loop is implemented digitally using the Xilinx blockset integrated with Matlab/Simulink. The three-phase digital phase-locked loop (TDPLL) is elaborately designed with the parameters defined in detail. The AC-DC converter (rectifier) model with the TDPLL is built and simulated in the high-speed VHS-ADC simulation platform from Canada. The simulation and test results show the TDPLL is locked right after the different three-phase voltage disturbances and very suitable for control of the rectifier with high parallelism through space vector pulse width modulation (SVPWM). http://dx.doi.org/10.11591/telkomnika.v11i7.2850
Performance Characteristics of Six-Phase Induction Generator for Renewable Power Generation
Alok Kumar Mohanty;
K B Yadav
Indonesian Journal of Electrical Engineering and Computer Science Vol 5, No 2: February 2017
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v5.i2.pp299-308
This paper presents the performance behavior of a multi-phase induction generator operating in six-phase mode. An experimental analysis has been done to determine operating characteristics of the six-phase machine to illustrate the advantageous features of the machine as compared to its three phase counterpart. The machine is configured to operate as a standalone power source in conjunction with a DC prime mover. The multi-phase machine can operate with one three phase capacitor bank which does not lead to complete shutdown of the system during fault conditions across one of its two sets of its stator windings. In the analysis the machine is connected to different capacitor configuration and the influence of these connections on the machine performance during no load and load have been implemented. Experimental results include voltage build up of the machine with different excitation capacitors at both sets of stator windings with changing speed during no load condition, resistive load condition and resistive inductive load condition with simple shunt and short shunt configuration.
A Survey of Video Based Action Recognition in Sports
Nur Azmina Rahmad;
Muhammad Amir As'ari;
Nurul Fathiah Ghazali;
Norazman Shahar;
Nur Anis Jasmin Sufri
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 3: September 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v11.i3.pp987-993
Sport performance analysis which is crucial in sport practice is used to improve the performance of athletes during the games. Many studies and investigation have been done in detecting different movements of player for notational analysis using either sensor based or video based modality. Recently, vision based modality has become the research interest due to the vast development of video transmission online. There are tremendous experimental studies have been done using vision based modality in sport but only a few review study has been done previously. Hence, we provide a review study on the video based technique to recognize sport action toward establishing the automated notational analysis system. The paper will be organized into four parts. Firstly, we provide an overview of the current existing technologies of the video based sports intelligence systems. Secondly, we review the framework of action recognition in all fields before we further discuss the implementation of deep learning in vision based modality for sport actions. Finally, the paper summarizes the further trend and research direction in action recognition for sports using video approach. We believed that this review study would be very beneficial in providing a complete overview on video based action recognition in sports.
A 5G graphene antenna produced by screen printing method
Siti Nor Hafizah Sa’don;
Mohd Haizal Jamaluddin;
Muhammad Ramlee Kamarudin;
Fauzan Ahmad;
Samsul Haimi Dahlan
Indonesian Journal of Electrical Engineering and Computer Science Vol 15, No 2: August 2019
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v15.i2.pp950-955
The save and fast manufacturing are required in order to achieve 5G technology. However, there are many kinds of manufacturing antenna which are depending on material applied in the antenna itself. Each type of manufacturing also has its own advantages and drawback. In this article, a graphene antenna for 5G applications is manufactured using screen printing method. A fine mesh resolution of 120 µm is used to print the antenna accurately. This kind of printing has capability to produce antenna in less than 5 minutes. The antenna made by conductive graphene ink has size of 11.8 x 12.2 x 0.076 mm3 and produced within a small amount of graphene ink. The measured antenna resonates at 15.04 GHz with reflection coefficient magnitude of -12.05 dB and percentage of impedance bandwidth is 30 % which is in the range of 13.3 to 18.0 GHz. The radiation pattern at E-plane and H-plane of the graphene antenna are simulated and measured where the result obtained are comparable.
A New Algorithm for Protection of Small Scale Synchronous Generators Against Transient Instability
Zinat Khosravi;
Alireza Saffarian
Indonesian Journal of Electrical Engineering and Computer Science Vol 16, No 3: December 2015
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v16.i3.pp454-462
Today, installation of small generators has been increased because of their considerable benefits in distribution systems in distributed generation. One of the most important problems for transient stability is the effects of the faults of system. Small scale generators have low constant inertia and protection relays have slow performance in distribution systems. Therefore transient instability is a probable phenomenon for the systems with these generators. In this paper, dynamic response of generator has been studied in different fault conditions and then by introducing the concept of " critical fault clearing time ", the sensitivity of this time to the fault type and also fault location parameters have been studied. Then a new protection scheme has been proposed to prevent of transient instability for small scale generator. This protection scheme uses a new evolutionary algorithm based on the active power of generator and critical fault clearing time. The proposed relay can prevent of wrong and unwanted performance. Furthermore it can disconnect the generator from the system in three phase fault near of the bus-bar before its instability. Simulation results show reliable performance of the proposed relay against system transients.