Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

25,002 Article Results

Towards Behavior Control for Evolutionary Robot Based on RL with ENN

https://ijra.iaescore.com/index.php/IJRA/article/view/890
Jingan Yang , Yanbin Zhuang , Chunguang Li
This paper proposes a behavior-switching control strategy of anevolutionary robotics based on Artificial NeuralNetwork (ANN) and Genetic Algorithms (GA). This method is able not only to construct thereinforcement learning models for autonomous robots and evolutionary robot modules thatcontrol behaviors and reinforcement learning environments, and but also to perform thebehavior-switching control and obstacle avoidance of an evolutionary robotics (ER) intime-varying environments with static and moving obstacles by combining ANN and GA.The experimental results on thebasic behaviors and behavior-switching control have demonstrated that ourmethod can perform the decision-making strategy and parameters set opimization ofFNN and GA by learning and can escape successfully from the trap of a localminima and avoid \emph{"motion deadlock" status} of humanoid soccer robotics agents,and reduce the oscillation of the planned trajectory betweenthe multiple obstacles by crossover and mutation. Some results of the proposed algorithmhave been successfully applied to our simulation humanoid robotics soccer team CIT3Dwhich won \emph{the 1st prize} of RoboCup Championship and ChinaOpen2010 (July 2010) and \emph{the $2^{nd}$ place}of the official RoboCup World Championship on 5-11 July, 2011 in Istanbul, Turkey.As compared with the conventional behavior network and the adaptive behavior method,the genetic encoding complexity of our algorithm is simplified, and the networkperformance and the {\em convergence rate $\rho$} have been greatlyimproved.DOI: http://dx.doi.org/10.11591/ijra.v1i1.259
Volume: 1
Issue: 1
Page: 31-48
Publish at: 2012-03-01

Robot Kinematics, using Dual Quaternions

https://ijra.iaescore.com/index.php/IJRA/article/view/889
Mahmoud Gouasmi , Mohammed Ouali , Fernini Brahim
From the point of view of classical mechanics, deriving the equations of motion for systems of coupled rigid bodies is regarded as a straightforward procedure: once a suitable set of generalized coordinates and reference frames have been chosen, what remains is to either apply Lagrange’s equations or Newton and Euler’s equations to obtain the differential equations of motion. As the complexity of multibody system increases, the need for more elegant formulation of the equation of motion becomes an issue of paramount importance. Our primary focus is on the kinematic analysis of rigid bodies and serial manipulators (robotic systems)  using simultaneously, both homogeneous transformations (4x4) matrices and Dual Quaternions, for the sake of results comparisons (cost,complexity,storage capacity etc.) . This paper has been done mainly for educational and peadagogical purposes, hoping that the scientific community will finally adopt and use Dual Quaternions at least when dealing with multibody systems and specially robotics.DOI: http://dx.doi.org/10.11591/ijra.v1i1.275
Volume: 1
Issue: 1
Page: 13-30
Publish at: 2012-03-01

Performance Analysis for Bit-Error-Rate of DS-CDMA Sensor Network Systems with Source Coding

10.12928/telkomnika.v10i1.774
Ali M.; University of Basra Fadhil , Haider M.; University of Basra AlSabbagh
One of the distinguished techniques used with wireless sensor networks to access the network is utilizing direct sequence-code division multiple access. However, amount of consumed energy and multiple access interference are still considered as the main problems with employing such networks. The consumed energy and interference are rising when number of users (receivers) increases. Therefore, this paper is conducted to investigate mitigating influence these factors through analyzing the minimum energy coding which exploits redundant bits for saving power with employing radio frequency link and on-off-keying modulation. These factors are analyzed and discussed for several levels of expected errors in the utilizing channel, through the bit error rates and amount of signal to noise ratio for different number of users. 
Volume: 10
Issue: 1
Page: 165-170
Publish at: 2012-03-01

Demand Shifting Bidding in a Hybrid System with Volatile Wind Power Generation

10.12928/telkomnika.v10i1.758
D.K. Agrawal; Maulana Azad National Institute Of Technology D.K. Agrawal , N.P. Patidar; Maulana Azad National Institute Of Technology N.P. Patidar , R.K. Nema; Maulana Azad National Institute Of Technology R.K. Nema
Price responsive demand shifting bidding mechanism is discussed as an alternative solution to deal with intermittency in wind generation. This paper proposes a formulation of social welfare equation with price responsive demand shifting bidding and economic emission dispatch with emphasis on integration of wind power. The analysis is based on the IEEE 30 bus test system generation data, with conventional and wind generation plant over a period of 24 hours. It has been demonstrated that the proposed approach leads to reduction in emission as well deal with intermittency in wind generation.
Volume: 10
Issue: 1
Page: 33-42
Publish at: 2012-03-01

Gabor-based Face Recognition with Illumination Variation using Subspace-Linear Discriminant Analysis

10.12928/telkomnika.v10i1.767
Hendra; Institut Teknologi Sepuluh Nopember Surabaya Kusuma , Wirawan; Institut Teknologi Sepuluh Nopember Surabaya Wirawan , Adi; Institut Teknologi Sepuluh Nopember Surabaya Soeprijanto
            Face recognition has been an active research topic in the past few decades due to its potential applications. Accurate face recognition is still a difficult task, especially in the case that illumination is unconstrained. This paper presents an efficient method for the recognition of faces with different illumination by using Gabor features, which are extracted by using log-Gabor filters of six orientations and four scales. By Using sliding window algorithm, these features are extracted at image block-regions. Extracted features are passed to the principal component analysis (PCA) and then to linear discriminant analysis (LDA). For development and testing we used facial images from the Yale-B databases. The proposed method achieved 86–100 % rank 1 recognition rate.
Volume: 10
Issue: 1
Page: 119-128
Publish at: 2012-03-01

Comparasion between Oil Immersed and SF6 Gas Power Transformers Ratings

10.12928/telkomnika.v10i1.797
Osama Elsayed; Cairo University Gouda , Mohamed Dessoky; Cairo University Ali , Ali-Hassan; Cairo University Ali-Hassan
           Power transformers present the largest portion of the capital investment in addition the power transformer remains oil immersed which presents a fire hazard that is particularly objectionable in urban and metropolitan environment. After careful studies of various alternatives to conventional transformer technology to produce a gas insulated power transformer with increased mega volt-ampere ratings, gas insulated power transformer has been developed with a use with non flammable SF6 gas. For changing the insulating material from oil to SF6 gas a comparative study between these types of transformers should be made. In this paper two mathematical models are suggested and simulated by computer programs to calculate the temperature of the cooling mediums and transformer windings. The obtained results are in agreement wit the measured values in the field.
Volume: 10
Issue: 1
Page: 43-54
Publish at: 2012-03-01

Temperature Control System in Closed House for Broilers Based on ANFIS

10.12928/telkomnika.v10i1.762
Alimuddin; University of Sultan Ageng Tirtayasa, Bogor Agricultural University Alimuddin , Kudang Boro; Bogor Agricultural University Seminar , I Dewa Made; Bogor Agricultural University Subrata , Nakao; University of Tsukuba Nomura , Sumiati; Bogor Agricultural University Sumiati
 Indonesia is a tropical country with high ambient temperatures for broilers since daily temperature reaches an average daily temperature of 360C (maximum) and 320 C (minimum); whereas the optiml temperature for broilers is in the range of 28-300C. Thefefore, midle or large scale broiler industries have been using a control system to maintain the optimal temperature within a broiler house. Therefore, the role of a control system for regulating environmental parameters, not only temperature but also humidity, light intensity, and amonia content level, is very critical and relevant for better broiler production. This study aims to design an ANFIS control system for controlling the temperature inside a broiler house (closed house) for broiler. Data is collected at three different periods of the starter period (5 days): 29.50C-30.900C, a period of 25 days is a grower-29.0C 34.20C, and the finisher of 30 days is obtained 33.20C. Set point control simulation using the same temperature 290C for starter, grower and finisher period. The simulation results show the output in a closed house temperature fluctuates around set point the 290C-340C.
Volume: 10
Issue: 1
Page: 75-82
Publish at: 2012-03-01

Intelligent Monitoring System on Prediction of Building Damage Index using Neural-Network

10.12928/telkomnika.v10i1.773
Mardiyono; Politeknik Negeri Semarang Mardiyono , Reni; University of Riau Suryanita , Azlan; Universiti Teknologi Malaysia Adnan
An earthquake potentially destroys a tall building. The building damage can be indexed by FEMA into three categories namely immediate occupancy (IO), life safety (LS), and collapse prevention (CP). To determine the damage index, the building model has been simulated into structure analysis software. Acceleration data has been analyzed using non linear method in structure analysis program. The earthquake load is time history at surface, PGA=0105g. This work proposes an intelligent monitoring system utilizing artificial neural network to predict the building damage index. The system also provides an alert system and notification to inform the status of the damage. Data learning is trained on ANN utilizing feed forward and back propagation algorithm. The alert system is designed to be able to activate the alarm sound, view the alert bar or text, and send notification via email to the security or management. The system is tested using sample data represented in three conditions involving IO, LS, and CP. The results show that the proposed intelligent monitoring system could provide prediction of up to 92% rate of accuracy and activate the alert. Implementation of the system in building monitoring would allow for rapid, intelligent and accurate prediction of the building damage index due to earthquake.
Volume: 10
Issue: 1
Page: 155-164
Publish at: 2012-03-01

Five-Level Common-Emitter Inverter Using Reverse-Blocking IGBTs

10.12928/telkomnika.v10i1.757
Suroso; Jenderal Soedirman University Suroso , Toshihiko; Shizuoka University Noguchi
In a high switching frequency operation of current-source inverter (CSI), a conventional way to obtain unidirectional power switches is by connecting discrete diodes in series with the high speed power switches, i.e. power MOSFETs or IGBTs. However, these discrete diodes will cause extra losses to the power converter. This paper presents experimental test results of high switching frequency five-level common-emitter CSI using the emerging unidirectional power switches, i.e. reverse blocking (RB)-IGBTs. Experimental tests were also conducted to compare the performance between power MOSFETs in series with the discrete diodes, and the RB-IGBTs having inherent reverse blocking capability. The results show that using RB-IGBTs, the efficiency of the power converter increase. However, it is also confirmed that the recently available RB-IGBTs have slow reverse recovery current than the discrete fast-recovery diodes connected in series with power MOSFETs.
Volume: 10
Issue: 1
Page: 25-32
Publish at: 2012-03-01

Efficient Kernel-based Two-Dimensional Principal Component Analysis for Smile Stages Recognition

10.12928/telkomnika.v10i1.766
Rima Tri; University of Trunojoyo Madura Wahyuningrum , Fitri; University of Trunojoyo Madura Damayanti
 Recently, an approach called two-dimensional principal component analysis (2DPCA) has been proposed for smile stages representation and recognition. The essence of 2DPCA is that it computes the eigenvectors of the so-called image covariance matrix without matrix-to-vector conversion so the size of the image covariance matrix are much smaller, easier to evaluate covariance matrix, computation cost is reduced and the performance is also improved than traditional PCA. In an effort to improve and perfect the performance of smile stages recognition, in this paper, we propose efficient Kernel based 2DPCA concepts. The Kernelization of 2DPCA can be benefit to develop the nonlinear structures in the input data. This paper discusses comparison of standard Kernel based 2DPCA and efficient Kernel based 2DPCA for smile stages recognition. The results of experiments show that Kernel based 2DPCA achieve better performance in comparison with the other approaches. While the use of efficient Kernel based 2DPCA can speed up the training procedure of standard Kernel based 2DPCA thus the algorithm can achieve much more computational efficiency and remarkably save the memory consuming compared to the standard Kernel based 2DPCA.
Volume: 10
Issue: 1
Page: 113-118
Publish at: 2012-03-01

CT-FC: more Comprehensive Traversal Focused Crawler

10.12928/telkomnika.v10i1.777
Siti; Surabaya Adhitama Institute of Technology Maimunah , Husni S; Bandung Institute of Technology Sastramihardja , Dwi H; Bandung Institute of Technology Widyantoro , Kuspriyanto; Bandung Institute of Technology Kuspriyanto
 In today’s world, people depend more on the WWW information, including professionals who have to analyze the data according their domain to maintain and improve their business. A data analysis would require information that is comprehensive and relevant to their domain. Focused crawler as a topical based Web indexer agent is used to meet this application’s information need. In order to increase the precision, focused crawler face the problem of low recall. The study on WWW hyperlink structure characteristics indicates that many Web documents are not strong connected but through co-citation & co-reference. Conventional focused crawler that uses forward crawling strategy could not visit the documents in these characteristics. This study proposes a more comprehensive traversal framework. As a proof, CT-FC (a focused crawler with the new traversal framework) ran on DMOZ data that is representative to WWW characteristics. The results show that this strategy can increase the recall significantly.
Volume: 10
Issue: 1
Page: 189-198
Publish at: 2012-03-01

IEEE 802.11n Physical Layer Implementation on Field Programmable Gate Array

10.12928/telkomnika.v10i1.761
Hendra; Universitas Islam Indonesia Setiawan , Yuhei; Kyushu Institute of Technology Nagao , Masayuki; Kyushu Institute of Technology Kurosaki , Hiroshi; Kyushu Institute of Technology Ochi
Register transfer level (RTL) development is a time cost step that requires high diligence and fidelity to get the valid interpretation of abstraction function of digital circuit. In this research, we introduce and prove that Model-Based Design Process (MBDP) is an effective and efficient way to develop a RTL complex system such as wireless communication. Using MBDP flow, we interpret, develop, and verify the physical layer RTL of a new standard that ratified on the end 2009, i.e. IEEE 802.11n wireless local area network (WLAN). The result of this research is a prototyping FPGA StratixII EP2S180 that has properly worked as a 2x2 MIMO WLAN with maximum throughput 144 Mbps. 
Volume: 10
Issue: 1
Page: 67-74
Publish at: 2012-03-01

Compressed Sensing for Thoracic MRI with Partial Random Circulant Matrices

10.12928/telkomnika.v10i1.772
Windra; Ma Chung University Swastika , Hideaki; Chiba University Haneishi
The use of circulant matrix as the sensing matrix in compressed sensing (CS) scheme has recently been proposed to overcome the limitation of random or partial Fourier matrices. Aside from reducing computational complexity, the use of circulant matrix for magnetic resonance (MR) image offers the feasibility in hardware implementations. This paper presents the simulation of compressed sensing for thoracic MR imaging with circulant matrix as the sensing matrix. The comparisons of reconstruction of three different type MR images using circulant matrix are investigated in term of number of samples, number of iteration and signal to noise ratio (SNR). The simulation results showed that circulant matrix works efficiently for encoding the MR image of respiratory organ, especially for smooth and sparse image in spatial domain.
Volume: 10
Issue: 1
Page: 147-154
Publish at: 2012-03-01

Operation of a Fuzzy Controlled Half-Bridge DC-Converter as a Welding Current-Source

10.12928/telkomnika.v10i1.756
Zahra; Islamic Azad University Malekjamshidi , Mohammad; Islamic Azad University Jafari , Kourosh; Arsanjan Technical and Professional Educating Center Mahmoodi
 A new Fuzzy controlled welding machine (FCWM) current source is introduced in this paper and the results of the new control method are explained. The Fuzzy controller is applied to the welding machine to improve some problems of welding process. The new intelligent controller guaranties a constant current during welding to improve welding quality. It also provides some features such as hot-start and anti-stuck function and a standby mode for energy saving. The effectiveness of this intelligent welding machine was proven by the experimental results and durable test.  The results show that designed FCWM can be used in mobile welding industries.
Volume: 10
Issue: 1
Page: 17-24
Publish at: 2012-03-01

Multiobjective H2/H∞ Control Design with Regional Pole Constraints

10.12928/telkomnika.v10i1.765
Hardiansyah; Tanjungpura University Hardiansyah , Junaidi; Tanjungpura University Junaidi
This paper presents multiobjective H2/H∞ control design with regional pole constraints. The state feedback gain can be obtained by solving a linear matrix inequality (LMI) feasibility problem that robustly assigns the closed-loop poles in a prescribed LMI region. The proposed technique is illustrated with applications to the design of stabilizer for a typical single-machine infinite-bus (SMIB) power system. The LMI-based control ensures adequate damping for widely varying system operating conditions. The simulation results illustrate the effectiveness and robustness of the proposed stabilizer.
Volume: 10
Issue: 1
Page: 103-112
Publish at: 2012-03-01
1 2 3
...
1666 1667
Show 1643 of 1667

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration