Articles
9,174 Documents
Optimal Feature Selection Technique for Mel Frequency Cepstral Coefficient Feature Extraction in Classifying Infant Cry with Asphyxia
A. Zabidi;
W. Mansor;
Khuan Y. Lee
Indonesian Journal of Electrical Engineering and Computer Science Vol 6, No 3: June 2017
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v6.i3.pp646-655
Mel Frequency Cepstral Coefficient is an efficient feature representation method for extracting human-audible audio signals. However, its representation of features is large and redundant. Therefore, feature selection is required to select the optimal subset of Mel Frequency Cepstral Coefficient features. The performance of two types of feature selection techniques; Orthogonal Least Squares and F-ratio for selecting Mel Frequency Cepstral Coefficient features of infant cry with asphyxia was examined. OLS selects the feature subset based on their contribution to the reduction of error, while F-Ratio selects them according to their discriminative abilities. The feature selection techniques were combined with Multilayer Perceptron to distinguish between asphyxiated infant cry and normal cry signals. The performance of the feature selection methods was examined by analysing the Multilayer Perceptron classification accuracy resulted from the combination of the feature selection techniques and Multilayer Perceptron. The results indicate that Orthogonal Least Squares is the most suitable feature selection method in classifying infant cry with asphyxia since it produces the highest classification accuracy.
A Comprehensive Review on Applications of Don’t Care Bit Filling Techniques for Test Power Reduction in Digital VLSI Systems
Sanjoy Mitra;
Debaprasad Das
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 3: December 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v12.i3.pp941-949
Massive power consumption during VLSI testing is a serious threat to reliability concerns of ubiquitous silicon industry. A significant amount of low-power methodologies are proposed in the relevant literature to address this issue of test mode power consumption and don’t care bit(X) filling approaches are one of them in this fraternity. These don’t care(X) bit filling techniques have drawn the significant attention of industry and academia for its higher compatibility with existing design flow as neither modification of the CUT is required nor they need to rerun the time-consuming ATPG process. This paper presents an empirical survey of those X-bit filling techniques, applied to mitigate prime two types of dynamic power dissipation namely shift power and capture power, occurred during full scan testing.
Analysis of Weak Position in Overhead line under Heavy Icing Condition by Finite Element Method
Gan Yan;
Liu Chao;
Ruan Jiangjun;
Li Jinliang;
Du Zhiye;
Hu Yuanchao
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 7: July 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v12.i7.pp5011-5021
Transmission tower is an important component of power system, and heavy iced transmission line has became one of the important factors against its safety and stability in China's power system these years but the transmission line designed from traditional standard can't endure the more worse environment. In this paper, for positioning the weak points of the transmission line under heavy icing accurately and providing accurate positional parameters to online monitoring devices, the strain section model is built to analysis their mechanical properties under icing and wind conditions .In proposed method, the coupling effect between tower and lines is considered, then the weak tower is picked out by strain section model that is combined with eight towers. The single one-tower-two-lines model of weak tower is built to simulate and verify the weak point accurately. Finally the better way is defined to get the location of weak structure combined with the advantages of both models.
Adaptive RBFNN Formation Control of Multi-mobile Robots with Actuator Dynamics
Li Yan-dong;
Zhu Ling;
Sun Ming
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 4: April 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
We study the problem of formation control and trajectory tracking for multiple nonholonomic mobile robots with actuator and formation dynamics. An adaptive neural-network (NN) control strategy that integrated kinematic controller with input voltages controller of actuator was proposed. A control law was designed by backstepping technique based on separation-bearing formation control structure of leader-follower. The radial basis function neural network (RBFNN) was adopted to achieve on-line estimation for the dynamics nonlinear uncertain part for follower and leader robots. The adaptive robust controller was adopted to compensate modeling errors of NN. This strategy not only overcomed all kinds of uncertainties of mobile robots, but also ensured the desired trajectory tracking of robot formation in the case of maintaining formation. The stability and convergence of the control system were proved by using the Lyapunov theory. The simulation results showed the effectiveness of this proposed method. DOI: http://dx.doi.org/10.11591/telkomnika.v11i4.2334
OpenGL 3D crowd evacuation simulation at universiti tun hussein onn malaysia (UTHM) hostel
Jamaludin, M.N;
Mohamad, S.;
Sunar, M.S.;
Isa, K.;
Hanifa, R.M.;
Nasir, F.M.;
Shah, S.M.
Indonesian Journal of Electrical Engineering and Computer Science Vol 16, No 2: November 2019
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v16.i2.pp1034-1041
Crowd simulation is the process of simulating characterized agents or entities using computer application to analyse it in virtual scene or virtual environment. This paper investigates the best route path for agents to act in avoiding the fire hazards with different designated type of stairs in shop lots that were converted to hostel dormitory for students. 3D social force agent’s model and 3D fire hazards were designed in Microsoft Visual Studio C++ software and OpenGL library. A research was conducted using social force model behaviour and were taken by 10 and 15 agents to analyse the time taken to complete the evacuation process. The acceleration produced where it is related with route path taken by agents, interaction forces of agents and interaction forces of wall are the main research system to analyse agents’ behaviour during simulation. Different simulations have been used to determine the best and fastest route taken by agents. In summary, the lower the number of agents, the lower the time allocated by agents to complete the evacuation. Finally, less number of agents using the designated straight stairs gave a lower time to complete evacuation process and reached high level of security to avoid being exposed to fire hazards.
Improved reliable multilevel inverter for renewable energy systems
Sujatha M;
A.K. Parvathy
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.pp1141-1147
New improved multilevel inverter (MLI) topology for Renewable energy systems is proposed in this paper. Cascaded multilevel inverters (CMLI) produce an output voltage level depending on the number of individual sources connected. The main drawback of CMLI is, as the output voltage level increases in number, the switches used in the device also increases and hence the complexity of the circuit increases. As the number of switches increases, the reliability of the circuit decreases. In this paper a novel MLI topology, which employs lesser number of switches, is proposed. A simulation model of CMLI and the proposed MLI has been built in MATLAB/SIMULINK. The reliability of the CMLI and the new topology MLI is analyzed by using MIL-HDBK-217.
Design Flexural Piezoelectric Acoustic Transducers Array based d33 Mode Polarization
K.A. Ahmad;
A. Abd Manaf;
Z. Hussain Hussain;
Z. Janin
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 1: April 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v10.i1.pp59-65
Piezoelectric Acoustic Transducer (PAT) is a transducers used in many application such as medical diagnostic, medical ultrasonic imaging and underwater acoustic applications. Latest research, PAT were investigated in marine application and underwater acoustic imaging. Conventional PAT is design based on sensing element, Piezoelectric Material, matching layer and backing layer. But the conventional method still has problem with issues of narrow bandwidth, directivity and low sensitivity. This problem is occurred when the transducer need to increase the image resolution. The size of single element will become smaller to meet the requirement of high resolution. PZT-5H have high piezoelectric constant (d31) and low dielectric loss. It is chosen as sensing element in this design of PAT because it will increase the sensitivity of transducers. The PAT is design based on d33 mode polarization to improve the receiving sensitivity. The fabrication process are included wet etching on Printed Circuit Board (PCB), spin coated Polydimethylsiloxane (PDMS), and baked transducer on hot plate. PAT is characterized using Pulse-Echo method. Pulse-Echo method will determine the sensitivity, directivity and operating bandwidth of acoustic transducers in underwater applications. Open circuit receiving voltage (OCRV) is voltage response to determine the sensitivity of acoustic transducer. The commercial projector and hydrophone will calibrate to obtain the reliability of result. In cross talk test, at some particular frequency, Pin 2 and Pin 3 have low sensitivity value. It is because Pin 2 and Pin 3 received low acoustic wave pressure. The PAT array based d33 mode polarization shows it has more receiving sensitive compared to commercial acoustic transducers. The design transducer has sensitivity at -56 dB re 1V/µPa at resonance frequency, 100kHz and fractional bandwidth at 30%.
Training on professional foreign language for students of engineering specialties: implementation of electronic technology
Sergei V.Smirnov;
Aygul Z. Ibatova
Indonesian Journal of Electrical Engineering and Computer Science Vol 18, No 1: April 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v18.i1.pp301-309
The purpose of our work is to check the effectiveness of the principle of systematic in the process of teaching professional foreign language to the engineering specialties. The laboratory work contains information lexical programs for the introduction of active lexical lessons, vocabulary and grammar exercises, and questions to the texts of lessons, designated for self-control and mutual control. The authors presented the results of the implementation of the system principle in the pedagogical process, namely the possibility of providing systematic construction of methodical literature and construction of intra subject links. The laboratory work, thanks to which there is an actualization and improvement of basic knowledge and skills, as well as the motivation of educational activity - is the form of realization of this principle. The students have an opportunity to demonstrate the independence in performing communicative actions in the professional sphere, provided by the program, to automate their skills, to conduct the self-study and self-monitoring of knowledge and skills, as well as to make their correction.
An Optimized Neural Network Classifier for Automatic Modulation Recognition
Li Cheng;
Jin Liu
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 2: February 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Automatic modulation recognition which is one of the key technologies in no-cooperative communications has extensive application prospects in civilian and military fields. The design of classifier played a decisive role in recognition results. The classifier based on back propagation (BP) neural network is better in the existing methods. However, the traditional back propagation neural network (BPNN) have some well-known disadvantages. This study investigates the design of a classifier for recognition of six common digital modulations. This classifier based on BP neural network trained by improved particle swarm optimization (PSO) which is applied as a local search algorithm to find the optimal weights and thresholds of BPNN. The simulation experiment results demonstrate that the proposed classifier has a higher recognition accuracy than other classifiers. DOI : http://dx.doi.org/10.11591/telkomnika.v12i2.3930
Pose Error Analysis Model Based on Binocular Vision for Rigid-Body
Fenglian Niu
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 12: December 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
In order to satisfy the orientationmeasuring requirements of rigid-body such as work piece, cutting tool inindustry and medical instrumentsfor invasive surgery, this paper presents a binocularvision detection technique based on spatial position information of markers toextract rigid-body pose information and analyzes the pose accuracy of rigid-bodyusing the principalcomponent analysis(PCA) and the least square method(LSM) when spatial position error of markers exist. The simulation experiment demonstrates themaximum angle error of orientation is about 0.59 degree when the position error ofmarkers satisfy the Gaussian distribution with the meanis zero and thestandard deviation is 0~3mm. The experimental results verify this method canrobustly solve the orientation of rigid body using the position information ofmarkers with position errors, and it provides a theoretical and experimentalbasis for orientation measurement of rigid body. http://dx.doi.org/10.11591/telkomnika.v12i12.6136