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

30,547 Article Results

Recent advances in LVCSR : A benchmark comparison of performances

10.11591/ijece.v7i6.pp3358-3368
Rahhal Errattahi , Asmaa El Hannani
Large Vocabulary Continuous Speech Recognition (LVCSR), which is characterized by a high variability of the speech, is the most challenging task in automatic speech recognition (ASR). Believing that the evaluation of ASR systems on relevant and common speech corpora is one of the key factors that help accelerating research, we present, in this paper, a benchmark comparison of the performances of the current state-of-the-art LVCSR systems over different speech recognition tasks. Furthermore, we put objectively into evidence the best performing technologies and the best accuracy achieved so far in each task. The benchmarks have shown that the Deep Neural Networks and Convolutional Neural Networks have proven their efficiency on several LVCSR tasks by outperforming the traditional Hidden Markov Models and Guaussian Mixture Models. They have also shown that despite the satisfying performances in some LVCSR tasks, the problem of large-vocabulary speech recognition is far from being solved in some others, where more research efforts are still needed.
Volume: 7
Issue: 6
Page: 3358-3368
Publish at: 2017-12-01

Adaptive Antenna Selection and Power Allocation in Downlink Massive MIMO Systems

10.11591/ijece.v7i6.pp3521-3528
Adeeb Salh , Lukman Audah , Nor Shahida M Shah , Shipun A Hamzah
Massive multi-input, multi-output (MIMO) systems are an exciting area of study and an important technique for fifth-generation (5G) wireless networks that support high data rate traffic. An increased number of antenna arrays at the base station (BS) consumes more power due to a higher number of radio frequency (RF) chains, which cannot be neglected and becomes a technical challenge. In this paper, we investigated how to obtain the maximal data rate by deriving the optimal number of RF chains from a large number of available antenna arrays at the BS when there is equal power allocation among users. Meanwhile, to mitigate inter-user-interference and to compute transmit power allocation, we used the precoding scheme zero forcing beamforming (ZFBF). The achievable data rate is increased because the algorithm of ZFBF enables the choosing of the maximum power in relation to the optimal antenna selection. We conclude that the transmit power allocation  allows the use of less number of RF chains which provides the maximum achievable data rate depending on the optimal RF chain at the BS.
Volume: 7
Issue: 6
Page: 3521-3528
Publish at: 2017-12-01

A Guideline Tool for Ongoing Product Evaluation in Small and Medium-Sized Enterprises

10.11591/ijece.v7i6.pp3632-3642
Fouad Abdulameer Salman , Aziz Bin Deraman , Masita Binti Abdul Jalil
As consumer demand for user friendly software increases, usability evaluation is crucial to develop software systems which are easy to learn and use. However, implementation of usability evaluation is challenging for small and medium-sized enterprises (SMEs) due to factors such as lack of technical expertise, knowledge and experience of methods and standards. This results in neglect, or poorly executed evaluations of projects, resulting in software that disappoints and frustrates clients. To overcome this loss of competitiveness, we propose here a visual incorporation tool derived from ISO standards that would assist software development teams in SMEs in understanding and implementing usability evaluations. It shows fundamental Usability Engineering (UE) and Software Engineering (SE) activities and artifacts relevant to the usability evaluation and software development process, with potential incorporation points being highlighted. Dependencies and relationships are shown by links between activities and artifacts. Additionally, convergent artifacts of both disciplines were identified and shown. Evaluation of the proposed tool was based on the questionnaire results of software development practitioners from SMEs.
Volume: 7
Issue: 6
Page: 3632-3642
Publish at: 2017-12-01

Adjusting The Origin Of Buoyancy

10.11591/ijeecs.v8.i3.pp684-686
S. Ramaswami
Surf-riding actions in reliable attractive following oceans for cases with a variety of LCBs and Froude information are mimicked utilizing the numerical model. Comes concerning display that the surf-riding can't be forestalled by the modify of LCB. Be that as it may, it happens with an upper limit momentum when ship's focal point of lightness (COB) is stimulated towards stem contrasted with affecting towards stern, which is for the majority part since the distinctions on wave resistance brought concerning by the changing of LCB.
Volume: 8
Issue: 3
Page: 684-686
Publish at: 2017-12-01

Permanent Magnet Tubular Generator with Quasi-Halbach Array for Free-Piston Generator System

10.11591/ijpeds.v8.i4.pp1663-1672
Behrooz Rezaeealam
In this paper, the performance of a free-piston generator system with tubular single-phase stator winding is investigated for three different configurations of permanent magnet arrays on the mover: radial, rectangular quasi-Halbach and trapezoidal quasi-Halbach arrays. The optimal shape of the rectangular quasi-Halbach magnetization is obtained by employing an optimization technique called Imperialist Competitive Algorithm (ICA), and the results are compared with the previously developed permanent magnet linear generator (PMLG) with magnets of radial magnetization. Then, the resultant design of rectangular quasi-Halbach array, is changed to trapezoidal quasi-Halbach array and its performance is compared with other types of magnet arrays. The employed ICA is based on the analytical model of the magnetic flux distribution in air-gap, and is further verified by a nonlinear transient finite element (FE) model. The FE model has been developed to study the performance of the reciprocating PMLG. The accuracy of the proposed FE model is exemplified by comparing the calculated results with the experimental ones regarding the PMLG with radial magnetization.
Volume: 8
Issue: 4
Page: 1663-1672
Publish at: 2017-12-01

Intelligent Robotics Navigation System: Problems, Methods, and Algorithm

10.11591/ijece.v7i6.pp3711-3726
Siti Nurmaini , Bambang Tutuko
This paper set out to supplement new studies with a brief and comprehensible review of the advanced development in the area of the navigation system, starting from a single robot, multi-robot, and swarm robots from a particular perspective by taking insights from these biological systems. The inspiration is taken from nature by observing the human and the social animal that is believed to be very beneficial for this purpose. The intelligent navigation system is developed based on an individual characteristic or a social animal biological structure. The discussion of this paper will focus on how simple agent’s structure utilizes flexible and potential outcomes in order to navigate in a productive and unorganized surrounding. The combination of the navigation system and biologically inspired approach has attracted considerable attention, which makes it an important research area in the intelligent robotic system. Overall, this paper explores the implementation, which is resulted from the simulation performed by the embodiment of robots operating in real environments.
Volume: 7
Issue: 6
Page: 3711-3726
Publish at: 2017-12-01

Optimization of Empirical Modelling of Advanced Highly Strained In0.7Ga0.3As/In0.52Al0.48As pHEMTs for Low Noise Amplifier

10.11591/ijece.v7i6.pp3002-3009
W.M. Jubadi , F. Packeer , M. Missous
An optimized empirical modelling for a 0.25µm gate length of highly strained channel of an InP-based pseudomorphic high electron mobility transistor (pHEMT) using InGaAs–InAlAs material systems is presented. An accurate procedure for extraction is described and tested using the pHEMT measured dataset of I-V characteristics and related multi-bias s-parameters over 20GHz frequency range. The extraction of linear and nonlinear parameters from the small signal and large signal pHEMT equivalent model are performed in ADS. The optimized DC and S-parameter model for the pHEMT device provides a basis for active device selection in the MMIC low noise amplifier circuit designs.
Volume: 7
Issue: 6
Page: 3002-3009
Publish at: 2017-12-01

Investigation of Potential Grounding Compound for Portable Applications

10.11591/ijece.v7i6.pp3140-3146
N.A.M. Hasni , R. Abd-Rahman , H. Ahmad , N.A.M. Jamail , M. S. Kamaruddin , S.S. Ridzwan
This paper applies to the electrical engineering world by making earthing system portable in providing low and acceptable resistance path. The system is develop in a small scale portable earthing system against the massiveness of Earth and becomes leverage if soil at the place is not suitable for plant grounding system. Hence, this paper presents findings on the research of new grounding medium material that will be housed in a small scale enclosure which behaves like native earth related earthing system by using kaolin and bauxite. The data obtained from lightning flashover testing, morphological and chemical composition of material analysis indicated that bauxite is more useful for portable grounding system application much better than kaolin in term of zero reference point function. The portable earthing system can be apply to air aviation systems , railway systems and military sectors particularly for electronic equipment zero referencing.
Volume: 7
Issue: 6
Page: 3140-3146
Publish at: 2017-12-01

Classification of Road Damage from Digital Image Using Backpropagation Neural Network

10.11591/ijai.v6.i4.pp159-165
Sutikno Sutikno , Helmie Arif Wibawa , Prima Yusuf Budiarto
One of the biggest causes of death in the world is a traffic accident. Road damage is one of the cause factors from the traffic accident. To reduce this problem is required an early detection against road damage. This paper describes how to classify road damage using image processing and backpropagation neural network. Image processing is used to obtain binary image consists of a normalization, grayscaling, edge detection and thresholding, while the backpropagation neural network algorithm is used for classifying. The conclusion of this test that the algorithm is able to provide the accuracy rate of 83%. The results of this research may contribute to the development of road damage detection system based on the digital image so that the traffic accidents caused by road damage can be reduced.
Volume: 6
Issue: 4
Page: 159-165
Publish at: 2017-12-01

Real-Time Fatigue Analysis of Driver through Iris Recognition

10.11591/ijece.v7i6.pp3306-3312
Gopalakrishna K , Hariprasad S.A.
In recent days, the driver’s fault accounted for about 77.5% of the total road accidents that are happening every day. There are several methods for the driver’s fatigue detection. These are based on the movement of the eye ball using eye blinking sensor, heart beat measurement using Electro Cardio Gram, mental status analysis using ElectroEncephaloGram, muscle cramping detection, etc. However the above said methods are more complicated and create inconvenience for the driver to drive the vehicle. Also, these methods are less accurate. In this work, an accurate method is adopted to detect the driver’s fatigue based on status of the eyes using Iris recognition and the results shows that the proposed method is more accurate (about 80%) compared to the existing methods such as Eye blink Sensor method.
Volume: 7
Issue: 6
Page: 3306-3312
Publish at: 2017-12-01

Power Quality Improvement in QUCEST Larkana Campus by Using Three Types of Power Filters

10.11591/ijpeds.v8.i4.pp1876-1885
D. M. Soomro , S. C. Chong , Z. A. Memon , F. Abbasi
The increase of power electronic converters at the end-user side is unavoidable and it will cause current harmonic distortion and wide range of disturbance in the power system (PS). This paper presents current harmonic compensation for the test case of the Quaid-e-Awam University College of Engineering Sciences and Technology (QUCEST) Larkana campus in MATLAB SIMULINK by using three types of power filters i.e. passive, active and hybrid power filters. The purpose of this experiment and simulation model is to analyse and find out the best solution for reducing the current harmonic and unbalanced load condition at the incoming transformer to the campus. Moreover, this paper presents the testing and comparison of the active and hybrid power filters by using the combined design technique of harmonic compensate control system based on Unit Vector Template (UVT) and Instantaneous Reactive Power (IRP) theory. The simulation results allow to identify the effectiveness of the control system along with passive filter. Based on the testing and simulation results of three types of power filters, hybrid power filter has the maximum ability to mitigate the current harmonic in the system, and it also reduces the neutral current thus causing less stress in the existing system.
Volume: 8
Issue: 4
Page: 1876-1885
Publish at: 2017-12-01

Design and Implementation of an Embedded System for Software Defined Radio

10.11591/ijece.v7i6.pp3484-3491
A. E. Abdelkareem , Saad Mohammed Saleh , Ammar D. Jasim
In this paper, developing high performance software for demanding real-time embedded systems is proposed. This software-based design will enable the software engineers and system architects in emerging technology areas like 5G Wireless and Software Defined Networking (SDN) to build their algorithms. An ADSP-21364 floating point SHARC Digital Signal Processor (DSP) running at 333 MHz is adopted as a platform for an embedded system. To evaluate the proposed embedded system, an implementation of frame, symbol and carrier phase synchronization is presented as an application. Its performance is investigated with an on line Quadrature Phase Shift keying (QPSK) receiver. Obtained results show that the designed software is implemented successfully based on the SHARC DSP which can utilized efficiently for such algorithms. In addition, it is proven that the proposed embedded system is pragmatic and capable of dealing with the memory constraints and critical time issue due to a long length interleaved coded data utilized for channel coding.
Volume: 7
Issue: 6
Page: 3484-3491
Publish at: 2017-12-01

A Time-Frequency Transform Based Fault Detectionand Classificationof STATCOM Integrated Single Circuit Transmission Line

10.11591/ijpeds.v8.i4.pp1804-1813
Sanjay Kumar Mishra , S.C Swain , L.N Tripathy
  This paper discusses the time-frequency transform based fault detection and classification of STATCOM (Static synchronous compensator) integrated single circuit transmission line. Here, fast-discrete S-Transform (FDST) based time-frequency transformation is proposed for evaluation of fault detection and classification including STATCOM in transmission line. The STATCOM is placed at mid-point of transmission line. The system starts processing by extracting the current signals from both end of current transformer (CT) connected in transmission line. The current signals from CT’s are fed to FDST to compute the spectral energy (SE) of phase current at both end of the line. The differential spectral energy (DSE) is evaluated by subtracting the SE obtained from sending end and SE obtained from receiving end of the line. The DSE is the key indicator for deciding the fault pattern detection and classification of transmission line. This proposed scheme is simulated using MATLAB simulink R2010a version and successfully tested under various parameter condition such as fault resistance (Rf),source impedance (SI), fault inception angle (FIA) and reverse flow of current. The proposed approach is simple, reliable and efficient as the processing speed is very fast to detect the fault within a cycle period of FDT (fault detection time).
Volume: 8
Issue: 4
Page: 1804-1813
Publish at: 2017-12-01

Effective Technique for Improving Electrical Performance and Reliability of Fuel Cells

10.11591/ijpeds.v8.i4.pp1868-1875
A. Albarbar , M. Alrweq
To optimise the electrical performance of proton exchange membrane (PEM) fuel cells, a number of factors have to be precisely monitored and controlled. Water content is one of those factors that has great impact on reliability, durability and performance of PEM fuel cells. The difficulty in controlling water content lies in the inability to determine correct level of water accumulated inside the fuel cell. In this paper, a model-based technique, implemented in COMSOL, is presented for monitoring water content in PEM fuel cells. The model predicts, in real time, water content taking account of other processes occurring in gas channels, across gas diffusion layers (GDL), electrodes, and catalyst layer (CL) and within the membrane to minimize voltage losses and performance degradation. The level of water generated is calculated as function of cell’s voltage and current. Model’s performance and accuracy are verified using a transparent 500 mW PEM fuel cell. Results show model predicted current and voltage curves are in good agreement with the experimental measurements. The unique feature of this model is that, no special requirements are needed as only current, and voltage of the PEM fuel cell were measured thus, is expected to pave the path for developing non-intrusive control and monitoring systems for fuel cells.
Volume: 8
Issue: 4
Page: 1868-1875
Publish at: 2017-12-01

CHN and Swap Heuristic to Solve the Maximum Independent Set Problem

10.11591/ijece.v7i6.pp3583-3592
Bouhouch Adil , Loqman Chakir , El Qadi Abderrahime
We describe a new approach to solve the problem to find the maximum independent set in a given Graph, known also as Max-Stable set problem (MSSP). In this paper, we show how Max-Stable problem can be reformulated into a linear problem under quadratic constraints, and then we resolve the QP result by a hybrid approach based Continuous Hopfeild Neural Network (CHN) and Local Search. In a manner that the solution given by the CHN will be the starting point of the local search. The new approach showed a good performance than the original one which executes a suite of CHN runs, at each execution a new leaner constraint is added into the resolved model. To prove the efficiency of our approach, we present some computational experiments of solving random generated problem and typical MSSP instances of real life problem.
Volume: 7
Issue: 6
Page: 3583-3592
Publish at: 2017-12-01
Show 1542 of 2037

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