Articles

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

Filter Icon

Filters article

Years

FAQ Arrow
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

29,922 Article Results

Hardware Implementation of FIR Neural Network for Applications in Time Series Data Prediction

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/1458
Kuldeep S. Rawat , G.H. Massiha
Time series data prediction is used in several applications in the area of science and engineering. Time series prediction models have been implemented using statistical approaches, but recently, neural networks are being applied for times series prediction due to their inherent properties and capabilities. A variation of a standard neural network called as finite impulse response (FIR) neural network has proven to be highly successful in achieving higher degree of prediction accuracy when used over various time series prediction applications. These applications are time critical and involve huge amounts of computation that are slower when run on a general purpose processor and hence, a dedicated hardware is required. In this paper, authors present hardware implementation of an FIR neural network for applications in times series data prediction. The implementation is divided into (i) off-board, where the training algorithm and neural network configuration is implemented in Matrix Laboratory (MATLAB) and simulated with various benchmark time series data set and (ii) on-board, where the entire system is modeled in a hardware description language (HDL). The simulation experiment, hardware building blocks, the implementation framework, and the hardware design flow are discussed in this paper. The hardware resource utilization and timing information are also reported in the paper. DOI: http://dx.doi.org/10.11591/telkomnika.v14i1.7272 
Volume: 14
Issue: 1
Page: 130-139
Publish at: 2015-04-01

Capacitor Bank Voltage Equilibrium for MPPT in Single-Phase Single-Stage Five-Level Inverter for PV-Grid Application

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/1449
Leonardus Heru Pratomo , F. Danang Wijaya , Eka Firmansyah
Single-phase single-stage PV-Grid system using a five-level inverter has been investigated. Some of integration systems used two-stage converters, while others used single-stage converter. However, two-stage converters had a very complicated problem. The first converter acted as a maximum power point tracker to maximize power generated by sunlight energy to electric power, implemented by PV. The second stage was used as an interface to the grid. In single stage-converter was very simple in which an inverter was used for a maximum power point tracker and interface to the grid. This paper is designed to develop a single-stage PV-Grid system using a single-phase voltage source five-level inverter. The voltage equilibrium on capacitor was to make PV generate maximum power; hence, the equilibrium voltage between PV and five-level inverter output was proposed to deliver that maximum power generated by PV to the grid. Here, an analysis and a simulation were performed to demonstrate the design effectiveness. DOI: http://dx.doi.org/10.11591/telkomnika.v14i1.7646
Volume: 14
Issue: 1
Page: 62-71
Publish at: 2015-04-01

Control and Modelling of PV –Wind Hybrid Energy Sources for Desalination System

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/1444
Heba S. Abd-El Mageed , Hanaa M. Farghally , Faten H. Fahmy , Mohamed A. Abuo-Elmagd
Hybrid renewable energy based on PV and wind systems complemented with battery storage system are starting to play a vital role over the world to supply power to distant regions. This paper proposes the combination of lead acid battery system with a typical hybrid PV-wind energy system for supplying the electrical load of a desalination system at Mersa Matrouh. Solar and wind are sources of energy and battery unit is considered as a storage unit to meet the load demand. Simulation model with MATLAB/Simulink for the hybrid power system has been developed considering power supply variation in solar and wind hybrid power system caused due to disturbed power supply from wind turbine generator and solar system. A control strategy using Neural Network Control (NNC) is being offered and analyzed. The final result of the simulation indicates an effective operation of battery. DOI: http://dx.doi.org/10.11591/telkomnika.v14i1.7650
Volume: 14
Issue: 1
Page: 24-33
Publish at: 2015-04-01

Evaluation of Moving Object Detection Methods based on General Purpose Single Board Computer

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/1457
Agung Nugroho Jati , Ledya Novamizanti , Mirsa Bayu Prasetyo , Andy Ruhendy Putra
RGA and SKDA are two different methods which can be used to detect the object in image based processing. In order to support the moving surveillance camera system which proposed in Telkom University, RGA and SKDA have tested to be reviewed which more reliable to be implemented in a single board computer. In this paper, will be discussed about implementation and testing of two different methods of object detection using backgrounds subtraction. For implementation, each of them will be combined with Extended Kalman Filter in a Raspberry Pi. The parameter which have tested are memory and CPU usage, and system utilization.   The result shows that RGA is more reliable than SKDA to implemented in SBC because of less CPU usage and system utilization. DOI: http://dx.doi.org/10.11591/telkomnika.v14i1.7257
Volume: 14
Issue: 1
Page: 123-129
Publish at: 2015-04-01

Determination of Number of Channels in Multiple Access Techniques for Wireless Communications

10.11591/ijict.v4i1.pp1-6
Venkata Raghavendra Miriampally , G. Subba Rao , V Sudheer Raja
In wireless communications system, it is desirable to allow the subscriber to send simultaneously information to the base station while receiving information from base station. Multiple access techniques are used to allow many mobile users to share simultaneously a finite amount of radio spectrum. Frequency division multiple access (FDMA), time division multiple access(TDMA), and code division multiple access (CDMA) are the three major access techniques used to share the available bandwidth in a wireless communication system. In this paper we calculated the number of channels required for FDMA & TDMA techniques depending on various factors such as spectrum, channel band width etc.
Volume: 4
Issue: 1
Page: 1-6
Publish at: 2015-04-01

A Modified Bat Algorithm for Power Loss Reduction in Electrical Distribution System

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/1448
Djossou Adeyemi Amon
Losses on Electric Distribution System lines represent a major challenge for electric distribution companies since those losses refer to the amount of electricity injected into the distribution grids that are not paid by users. Network Optimization by system reconfiguration is one of the solutions among many others used to solve this problem. In this paper a modified version of new Meta Heuristic algorithm based on Bat behavior is proposed to find the best system configuration with a low loss rate, we present two different approaches: reduction of search space and introduction of sigmoid function to fit the algorithm to the problem. The main advantages of the proposed methodology are: easy implementation and less computational efforts to find an optimal solution. To demonstrate its efficiency the proposed scheme is tested on 33 Bus distribution system and the results show loss reduction rate of 33%. DOI:  http://dx.doi.org/10.11591/telkomnika.v14i1.7629 
Volume: 14
Issue: 1
Page: 55-61
Publish at: 2015-04-01

Near Optimal Convergence of Back-Propagation Method using Harmony Search Algorithm

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/1462
Abdirashid Salad Nur , Nor Haizan Mohd Radzi , Siti Mariyam Shamsuddin
Training Artificial Neural Networks (ANNs) is of great significanceand a difficult task in the field of supervised learning as its performance depends on underlying training algorithm as well as the achievement of the training process. In this paper, three training algorithms namely Back-Propagation Algorithm, Harmony Search Algorithm (HSA) and hybrid BP and HSA called BPHSA are employed for the supervised training of Multi-Layer Perceptron feed  forward type of Neural Networks (NNs)  by giving special attention to hybrid BPHSA. A suitable structure for data representation of NNs is implemented to BPHSA-MLP, HSA-MLP and BP-MLP. The proposed method is empirically tested and verified using five benchmark classification problemswhich are Iris, Glass, Cancer, Wine and Thyroid dataset on training NNs. The MSE, training time, and classification accuracy of hybrid BPHSA are compared with the standard BP and meta-heuristic HSA. The experiments showed that proposed method has better results in terms of convergence error and classification accuracy compared to BP-MLP and HSA-MLPmaking the BPHSA-MLPa promising algorithm for neural network training. DOI: http://dx.doi.org/10.11591/telkomnika.v14i1.7233
Volume: 14
Issue: 1
Page: 163-172
Publish at: 2015-04-01

A New Approach of Localized Human Blood Reheating Using High Frequency Converter

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/1453
Pradip Kumar Sadhu , Palash Pal , Animesh Halder , Ankur Ganguly , Nitai Pal , Prabir Bhowmik
The paper presents the human blood reheating technique for medical purposes with high frequency induction heating system. The temperature is analyzed to determine the heat distribution in different positions of human blood within the non metallic tank. In the proposed induction heating system, the inductive applicator is a primary working coil of the modified half bridge high frequency inverter and the RBCs within the blood will be working as secondary element. The simulation shows that the heating area can be effectively controlled by using the cylindrical shield with adjustable space. However, the efficiency of heat can be increased by varying the radius size of cylinder thereby more flux appears and more eddy emf is induced. Hence the resulting eddy current increases the refrigerated blood of range 1ºC- 6ºC to 37ºC. DOI: http://dx.doi.org/10.11591/telkomnika.v14i1.7262
Volume: 14
Issue: 1
Page: 97-102
Publish at: 2015-04-01

Study in Step by Step Electric Energy Meter Connection Detection Method

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/1452
Qing Zhiming , Fu Wang , Fei Wenli
Electric energy meter wiring error variety, detection method and circuit can only detect some kinds of wrong wiring at present, as the current transformer and current detection unit terminal short-circuit characteristics of conventional methods in existence, not take out stitches under the premise of not achieving detection. Based on this, this paper puts forward a step detection method, detection circuit of voltage and current lines one by one through right off and polarity of current, gradually show every junction point junction and the fault point. Through the Multisim software simulation, and developed a set of wire detecting device, simulation and experimental results prove that the method is correct. Compared with conventional methods, can be more comprehensive and faster connection detection fault location. DOI: http://dx.doi.org/10.11591/telkomnika.v14i1.7662 
Volume: 14
Issue: 1
Page: 90-96
Publish at: 2015-04-01

Development of Prototype model for Wireless based Controlled Pick and Place Robotic Vehicle

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/1455
Low Kok Hau , Gowrishankar Kasilingam , K. Nithiyananthan
The main aim of this research work is to develop and design a proto type model for a pick and place robotic vehicle with a soft catching gripper that can be controlled by android OS for remote operation. At the transmitting end using android application device, commands are sent to the receiver to control the movement of the robotic vehicle. Meanwhile at the receiving end four motors are interfaced to the microcontroller where two for them are used for arm movement while the other two are for the body movement. The android application device transmitter will acts as a remote control while the receiver end Bluetooth device is fed to the microcontroller to drive DC motors via motor driver IC for necessary work. Remote operation is achieved by any smart phone with AndroidOS; upon a GUI (Graphical User Interface) based touch screen operation. DOI: http://dx.doi.org/10.11591/telkomnika.v14i1.7370
Volume: 14
Issue: 1
Page: 110-115
Publish at: 2015-04-01

Demand Side Energy Management for Linear Programming Method

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/1450
N. Loganathan , K. Lakshmi
This paper presents an optimization method to the Demand Side Energy Management System (DSEMS) of a given consumer (e.g.an industrial compound or university campus) with respect to hourly electricity prices. The demands can be supplied through the main grid and stochastic Distributed Energy Resources (DERs), such as wind and solar power sources.  To solve this DSEMS problem and optimization algorithm based on Linear Programming (LP) approach has been implemented.  The objective of the proposed method is to maximize the utilization of the cluster of demands. This LP algorithm allows the cluster of demand to buy, store and sell energy at suitable times to adjust the hourly load level. To evaluate the performance of the proposed algorithm an IEEE 14 bus system was considered. The results shows that the cluster of demands of energy management system using the proposed approach increasing the efficiency and minimizing the losses than the existing methods. DOI: http://dx.doi.org/10.11591/telkomnika.v14i1.7570 
Volume: 14
Issue: 1
Page: 72-79
Publish at: 2015-04-01

Simulation of PCI Express™ Transaction Layer Using Hardware Description Language

10.11591/ijict.v4i1.pp7-12
Venkata Raghavendra Miriampally
PCI Express is a high-speed serial connection that operates more like a network than a bus. PCI Express will serve as a general purpose I/O interconnects for a wide variety of future computing and communications platforms. PCI Express (PCIe) is implemented with a split-transaction protocol that provides more bandwidth and is compatible with existing operating systems. PCI Express has three discrete logical layers: the Transaction Layer, the Data Link Layer, and the Physical Layer. This paper  analyze and simulates the function of Transaction layer IP core in the System Level with top-down design method, wrote the codes to implement Transaction Layer using Very high speed hardware description language (VHDL) and provided the simulation results using Active HDL Simulation tool. The simulation result shows that the designed IP core meets the required protocol specifications for the proper functioning of PCI Express Transaction layer. 
Volume: 4
Issue: 1
Page: 7-12
Publish at: 2015-04-01

Exploring Coal and Power Industries Integrated System in China

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/1443
Xu Peng
Differences of market force of coal and power industries caused this contradiction “market for coal, electricity for plans ”. C&P (Coal and power) industries issues around dual pricing system seriously hampered the development of C&P industries. This paper used the System Dynamics method to analyze the composition, characteristics and ways to build of the C&P industries integrated energy system, building feedback causal relationships of the C&P industries integrated energy system and their subsystems. Finally, this article established System Dynamics flow diagram. The analysis showed that C&P industries need rational planning, coordinating collaboration; strengthen the government's guide and regulation, continuously improve the transport capacity between enterprises. DOI: http://dx.doi.org/10.11591/telkomnika.v14i1.7618 
Volume: 14
Issue: 1
Page: 16-23
Publish at: 2015-04-01

Robust Pitch Detection Based on Recurrence Analysis and Empirical Mode Decomposition

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/1456
Jingfang Wang
A new pitch detection method is designed by the recurrence analysis in this paper, which is combined of Empirical Mode Decomposition (EMD) and Elliptic Filter (EF). The Empirical Mode Decomposition (EMD) of Hilbert-Huang Transform (HHT) are utilized tosolve the problem, and a noisy voice is first filtered on the elliptic band filter. The two Intrinsic Mode Functions (IMF) are synthesized by EMD with maximum correlation of voice, and then the pitch be easily divided. The results show that the new method performance is better than the conventional autocorrelation algorithm and cepstrum method, especially in the part that the surd and the sonant are not evident, and get a high robustness in noisy environment. DOI:  http://dx.doi.org/10.11591/telkomnika.v14i1.7216 
Volume: 14
Issue: 1
Page: 116-122
Publish at: 2015-04-01

Investigation of Neem Fatty Acid Ethyl Ester for Electric Power Generation

https://ijeecs.iaescore.com/index.php/IJEECS/article/view/1441
G. Vijaya Gowri , N. Kanagaraj , C. Muniraj
This paper presents biodiesel as an emerging renewable energy source which could meet substantially the very large growing electric energy demand maintaining the ecological balance. Biodiesel is a sustainable energy source which makes the environment out of pollution. The simplest process for biodiesel production called transesterification was carried out to produce biodiesel from neem oil. The output parameters such as speed, voltage, current and power are of the alternator are analysed for different loads using pure diesel, different biodiesel-diesel blends (80% biodiesel & 20% diesel, 60% biodiesel  & 40% diesel, 40% biodiesel & 60% diesel, 20% biodiesel  & 80% diesel) to an I.C engine. Results show that 20% biodiesel & 80% diesel blend (B20) produces the output with better efficiency. DOI: http://dx.doi.org/10.11591/telkomnika.v14i1.6978 
Volume: 14
Issue: 1
Page: 1-8
Publish at: 2015-04-01
Show 1730 of 1995

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