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

29,922 Article Results

A powerful comparison of deep learning frameworks for Arabic sentiment analysis

10.11591/ijece.v11i1.pp745-752
Youssra Zahidi , Yacine El Younoussi , Yassine Al-Amrani
Deep learning (DL) is a machine learning (ML) subdomain that involves algorithms taken from the brain function named artificial neural networks (ANNs). Recently, DL approaches have gained major accomplishments across various Arabic natural language processing (ANLP) tasks, especially in the domain of Arabic sentiment analysis (ASA). For working on Arabic SA, researchers can use various DL libraries in their projects, but without justifying their choice or they choose a group of libraries relying on their particular programming language familiarity. We are basing in this work on Java and Python programming languages because they have a large set of deep learning libraries that are very useful in the ASA domain. This paper focuses on a comparative analysis of different valuable Python and Java libraries to conclude the most relevant and robust DL libraries for ASA. Throw this comparative analysis, and we find that: TensorFlow, Theano, and Keras Python frameworks are very popular and very used in this research domain.
Volume: 11
Issue: 1
Page: 745-752
Publish at: 2021-02-01

A note on complex fuzzy subfield

10.11591/ijeecs.v21.i2.pp1048-1056
Muhammad Gulzar , Fareeha Dilawar , Dilshad Alghazzawi , M. Haris Mateen
In this paper, we introduce idea of complex fuzzy subfield and discuss its various algebraic aspects. We prove that every complex fuzzy subfield generate two fuzzy fields and shows that intersection of two complex fuzzy subfields is also complex fuzzy subfields. We also present the concept of level subsets of complex fuzzy subfield and shows that level subset of complex fuzzy subfield form subfield.  Furthermore, we extend this idea to define the notion of the direct product of two complex fuzzy subfields and also investigate the homomorphic image and inverse image of complex fuzzy subfield.
Volume: 21
Issue: 2
Page: 1048-1056
Publish at: 2021-02-01

Embedded processor system for controllable period-width multichannel pulse width modulation signals

10.12928/telkomnika.v19i1.16432
Mazin Rejab; Northern Technical University Khalil , Laith A.; Northern Technical University Mohammeed
This paper proposes a sophisticated embedded processor system configured on zynq-xc7z020 field programmable gate array (FPGA) device for generating four channels pulse width modulation signals with variable duty cycles and periods using embedded design techniques. The main advantages of the technique are the high ability to perform a simultaneous control on period and pulse width of the generated signals and a high system design adaptation to choose the number of input/output channels. Controlling the the period and the pulse width is achieved by injecting a digital signal to the designed system to manipulate embedded timers’ operation. Vivado design suite is used to develop the system hard ware in the integrated development environment where the processing unit and peripherals are instantiated and interconnected. A practical aplication program in C language is prepared to make the system act according to the target. The designed system can be used to drive multi-phase D.C to D.C convertors. The system performance is verified by using vivado logic analyzer and chipscope windows. The superiority of the proposed approach over other approaches is that it resulted in a multi-inputs/multi-outputs pulse width modulation system with high controllability on the pulse width and the period that ranges from 15 nsec to 60 sec.
Volume: 19
Issue: 1
Page: 220-228
Publish at: 2021-02-01

Interactive website on information dissemination

10.12928/telkomnika.v19i1.15048
Peter O.; University of Ilorin Sadiku , Roseline Oluwaseun; Landmark University Omu Aran Ogundokun , Opeyemi Eyitayo; Agricultural and Rural Management Training Institute Ogundokun , Asamu Aderonke; Univeristy of Ilorin Adebayo
A school is an educational institution for imparting knowledge to children. In an age where information acquisition about a school is assuming astronomical heights, the need for cost-effective and efficient information transmission methods cannot be overemphasized; hence the use of the website of a school to disseminate information is advised. This study examines the process of disseminating information on a school website using a college in the Northcentral of the six-geopolitical zone in Nigeria as a case study. A prior study of manually or locally dissemination of information in a school was carried out and its limitations are highlighted. A website that is able to handle processes like admission, comment, and newsletter has been analyzed and developed using hyper-text language, cascading style sheet, hypertext preprocessor. The study results in solving the information dissemination problem in the college with the development of an educational interactive website.
Volume: 19
Issue: 1
Page: 115-123
Publish at: 2021-02-01

Traffic sign detection optimization using color and shape segmentation as pre-processing system

10.12928/telkomnika.v19i1.16281
Handoko; Universitas Kristen Satya Wacana Handoko , Jehoshua Hanky; Universitas Kristen Satya Wacana Pratama , Banu Wirawan; Universitas Kristen Satya Wacana Yohanes
One of performance indicator of an Autonomous Vehicle (AV) is its ability to accomodate rapid environment changing; and performance of traffic sign detection (TSD) system is one of them. A low frame rate of TSD impacts to late decision making and may cause to a fatal accident. Meanwhile, adding any GPU to TSD will significantly increases its cost and make it unaffordable. This paper proposed a pre-processing system for TSD which implement a color and a shape segmentation to increase the system speed. These segmentation systems filter input frames such that the number of frames sent to AI system is reduced. As a result, workload of AI system is decreased and its frame rate increases. HSV threshold is used in color segmentation to filter frames with no desired color. This algorithm ignores the saturation when performing color detection. Further, an edge detection feature is employed in shape segmentation to count the total contours of an object. Using German Traffic Sign Recognition Benchmark dataset as model, the pre-processing system filters 97% of frames with no traffic sign objects and has an accuracy of 88%. TSD system proposed allows a frame rate improvement up to 32 FPS when YOLO algorithm is used.
Volume: 19
Issue: 1
Page: 173-181
Publish at: 2021-02-01

Evaluation of the stability enhancement of the conventional sliding mode controller using whale optimization algorithm

10.11591/ijeecs.v21.i2.pp744-756
Aws Mahmood Abdullah , Ali Mohsin Kaittan , Mustafa Sabah Taha
The proposed work is an attempt to investigate the stability of the nonlinear system by using a whale optimization algorithm as of one of the meta-heuristic optimization methods, and this investigation was conducted on a single inverted pendulum as a study model. The evaluation measures which were used in this article values of gain and sliding surface of the conventional sliding mode controller to illustrate the extent of the system`s stability. Furthermore, control action, the relationship between error and its derivative, desired, and actual position in addition to sliding response graphically showed the feasibility of the proposed solution. The attained results illustrated considerable improvement in the settling time and minimizing the impact of chattering behavior.
Volume: 21
Issue: 2
Page: 744-756
Publish at: 2021-02-01

Developing digital signal clustering method using local binary pattern histogram

10.11591/ijece.v11i1.pp872-878
Rashad J. Rasras , Bilal Zahran , Mutaz Rasmi Abu Sara , Ziad AlQadi
In this paper we presented a new approach to manipulate a digital signal in order to create a features array, which can be used as a signature to retrieve the signal. Each digital signal is associated with the local binary pattern (LBP) histogram; this histogram will be calculated based on LBP operator, then k-means clustering was used to generate the required features for each digital signal. The proposed method was implemented, tested and the obtained experimental results were analyzed. The results showed the flexibility and accuracy of the proposed method. Althoug different parameters of the digital signal were changed during implementation, the results obtained showed the robustness of the proposed method.
Volume: 11
Issue: 1
Page: 872-878
Publish at: 2021-02-01

Investigation on energy harvesting enabled device-to-device networks in presence of co-channel interference

10.12928/telkomnika.v19i1.16138
Thanh-Luan; Industrial University of Ho Chi Minh City Nguyen , Dinh-Thuan; Ton Duc Thang University Do
Energy harvesting from ambient radio-frequency (RF) sources has been a novel approach for extending the lifetime of wireless networks. In this paper, a cooperative device-to-device (D2D) system with the aid of energy-constrained relay is considered. The relays are assumed to be able to harvest energy from information signal and co-channel interference (CCI) signals broadcasted by nearby traditional cellular users and forward the source’s signal to its desired destination (D2D user) utilizing amplify-andforward (AF) relaying protocol. Time switching protocol (TSR) and power splitting protocol (PSR) are proposed to assist energy harvesting and information processing at the relay. The proposed approaches are applied in a model with three nodes including the source (D2D user), the relay and the destination (D2D user), the system throughput is investigated in terms of the ergodic capacity and the outage capacity, where the analytical results are obtained approximately. Our numerical results verify the our derivations, and also points out the impact of CCI on system performance. Finally, this investigation provide fundamental design guidelines for selecting hardware of energy harvesting circuits that satisfies the requirements of a practical cooperative D2D system.
Volume: 19
Issue: 1
Page: 27-35
Publish at: 2021-02-01

A two-stage power amplifier design for ultra-wideband applications

10.11591/ijece.v11i1.pp772-779
Idrees S. Al-Kofahi , Zaid Albataineh , Ahmad Dagamseh
In this paper, a two-stage 0.18 μm CMOS power amplifier (PA) for ultra-wideband (UWB) 3 to 5 GHz based on common source inductive degeneration with an auxiliary amplifier is proposed. In this proposal, an auxiliary amplifier is used to place the 2nd harmonic in the core amplified in order to make up for the gain progression phenomena at the main amplifier output node. Simulation results show a power gain of 16 dB with a gain flatness of 0.4 dB and an input 1 dB compression of about -5 dBm from 3 to 5 GHz using a 1.8 V power supply consuming 25 mW. Power added efficiency (PAE) of around 47% at 4 GHz with 50 Ω load impedance was also observed.
Volume: 11
Issue: 1
Page: 772-779
Publish at: 2021-02-01

A nested square-shape dielectric resonator for microwave band antenna applications

10.11591/ijece.v11i1.pp481-488
Ubaid Ullah , Ismail Ben Mabrouk , Muath Al-Hasan , Mourad Nedil , Mohd Fadzil Ain
In this paper, a nested square-shape dielectric resonator (NSDR) has been designed and investigated for antenna applications in the microwave band. A solid square dielectric resonator (SSDR) was modified systematically by introducing air-gap in the azimuth (ϕ-direction). By retaining the square shape of the dielectric resonator (DR), the well-known analysis tools can be applied to evaluate the performance of the NSDR. To validate the performance of the proposed NSDR in antenna applications, theoretical, simulation, and experimental analysis of the subject has been performed. A simple microstrip-line feeding source printed on the top of Rogers RO4003 grounded substrate was utilized without any external matching network. Unlike solid square DR, the proposed NSDR considerably improves the impedance bandwidth. The proposed antenna has been prototyped and experimentally validated. The antenna operates in the range of 12.34GHz to 21.7GHz which corresponds to 56% percentage bandwidth with peak realized gain 6.5dB. The antenna has stable radiation characteristics in the broadside direction. A close agreement between simulation and experimental results confirms the improved performance of NSDR in antenna applications.
Volume: 11
Issue: 1
Page: 481-488
Publish at: 2021-02-01

Extractive multi document summarization using harmony search algorithm

10.12928/telkomnika.v19i1.15766
Zuhair Hussein; Mustansiriyah University Ali , Ahmed Kawther; Mustansiriyah University Hussein , Haithem Kareem; Al-Mansour University College Abass , Elham; Mustansiriyah University Fadel
The exponential growth of information on the internet makes it troublesome for users to get valuable information. Text summarization is the process to overcome such a problem. An adequate summary must have wide coverage, high diversity, and high readability. In this article, a new method for multi-document summarization has been supposed based on a harmony search algorithm that optimizes the coverage, diversity, and readability. Concerning the benchmark dataset Text Analysis Conference (TAC-2011), the ROUGE package used to measure the effectiveness of the proposed model. The calculated results support the effectiveness of the proposed approach.
Volume: 19
Issue: 1
Page: 89-95
Publish at: 2021-02-01

Performance comparison between variants PID controllers and unity feedback control system for the response of the angular position of the DC motor

10.11591/ijece.v11i1.pp802-814
Mustafa A. Mhawesh
This paper proposed a detailed study for the response of angular position of the rotor of a DC motor. It is a comparative analysis to the behavior of the DC motor when the motor is alone and when it is with controllers. Furthermore, a comparison between the responses of controllers themselves. A conventional PID controller which was tuned by using Ziegler and Nichols method was proposed in this paper. Also, Modification PID controllers were proposed in this paper. The modification PID controllers are PI-D controller and I-PD controller. Mathematical calculations were done to get the transfer functions for the DC motor and the controllers. Time domain specifications and figures were obtained for each case by using Matlab program. The obtained results were summarized in tables. This paper determined which the controller is the best one depending on the obtained figures and the time domain specifications.
Volume: 11
Issue: 1
Page: 802-814
Publish at: 2021-02-01

Optimisation of LEACH protocol based on a game theory clustering approach for wireless sensor networks

10.11591/ijeecs.v21.i2.pp938-944
Yassine Oukessou , Mohamed Baslam , Mohamed Oukessou
The wireless sensor network clustering routing mechanism is the best multi-hop algorithm used to aggregate data from sensors to the base station. Therefore the elected nodes refuse to be a clusters heads CH and have a selfish and non cooperative behaviours in each group cluster. All that due to the high electric energy consumption, and especially that the most existing sensors are powered by batteries. In this paper, we will analyse the selfishness behaviour by using the most knowing mathematical model Game theory to improve the interaction decision making for the CH selection, and make a comparison with LEACH protocol.
Volume: 21
Issue: 2
Page: 938-944
Publish at: 2021-02-01

Finding the discriminative frequencies of motor electroencephalography signal using genetic algorithm

10.12928/telkomnika.v19i1.17884
Shaima Miqdad Mohamed; Northen Technical University Najeeb , Haider Th. Salim Al; Wasit University Rikabi , Shaima Mohammed; Northen Technical University Ali
A crucial part of the brain-computer interface is a classification of electroencephalography (EEG) motor tasks. Artifacts such as eye and muscle movements corrupt EEG signal and reduce the classification performance. Many studies try to extract not redundant and discriminative features from EEG signals. Therefore, this study proposed a signal preprocessing and feature extraction method for EEG classification. It consists of removing the artifacts by using discrete fourier transform (DFT) as an ideal filter for specific frequencies. It also cross-correlates the EEG channels with the effective channels to emphases the EEG motor signals. Then the resultant from cross correlation are statistical calculated to extract feature for classifying a left and right finger movements using support vector machine (SVM). The genetic algorithm was applied to find the discriminative frequencies of DFT for the two EEG classes signal. The performance of the proposed method was determined by finger movement classification of 13 subjects and the experiments show that the average accuracy is above 93 percent.
Volume: 19
Issue: 1
Page: 285-292
Publish at: 2021-02-01

Input switched closed-loop single phase SEPIC controlled rectifier with improved performances

10.11591/ijece.v11i1.pp1-8
Md. Shamsul Arifin , Mohammad Jahangir Alam
DC power supply has become the driving source for some essential modern applications. Thereby, DC power conditioning has become a significant issue for engineers. Typically used rectifiers associated with a bridge structure is nonlinear in nature. Thereby, the current at input side of the rectifier contains harmonics, which also flow through the power line. The presence of harmonics causes several interruptions and reduce power quality. In this regard, a new close loop SEPIC controlled rectifier is proposed in this paper. The conventional scheme is arranged with a rectifier connected to a DC-DC converter, which is an open loop system. Consequently, such system cannot regulate voltage at load varying condition. The proposed SEPIC controlled rectifier can regulate voltage under load varying condition for a wide range. Additionally, the performance in terms of total harmonic distortion (THD) of input current and power factor at AC side are also within satisfactory range for the closed loop configuration. The controlled rectifier has four operating phases associated with switching states and input voltage polarity. The close loop configuration also incorporates a current and a voltage loop at the feedback path. The comparative studies have been performed among the proposed closed loop construction, the open-loop structure as well as the conventional construction. The effectiveness of the proposed controlled rectifier is verified in terms of THD and input power factor considering the results obtained from simulation.
Volume: 11
Issue: 1
Page: 1-8
Publish at: 2021-02-01
1 2 3
...
1994 1995
Show 1021 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