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

30,185 Article Results

Semi-Supervised Keyphrase Extraction on Scientific Article using Fact-based Sentiment

10.12928/telkomnika.v16i4.5473
Felix Christian; Maranatha Christian University Jonathan , Oscar; Maranatha Christian University Karnalim
Most scientific publishers encourage authors to provide keyphrases on their published article. Hence, the need to automatize keyphrase extraction is increased. However, it is not a trivial task considering keyphrase characteristics may overlap with the non-keyphrase’s. To date, the accuracy of automatic keyphrase extraction approaches is still considerably low. In response to such gap, this paper proposes two contributions. First, a feature called fact-based sentiment is proposed. It is expected to strengthen keyphrase characteristics since, according to manual observation, most keyphrases are mentioned in neutral-to-positive sentiment. Second, a combination of supervised and unsupervised approach is proposed to take the benefits of both approaches. It will enable automatic hidden pattern detection while keeping candidate importance comparable to each other. According to evaluation, fact-based sentiment is quite effective for representing keyphraseness and semi-supervised approach is considerably effective to extract keyphrases from scientific articles.
Volume: 16
Issue: 4
Page: 1771-1778
Publish at: 2018-08-01

Deep Learning for Tuning Optical Beamforming Networks

10.12928/telkomnika.v16i4.8176
Herminarto; Universitas Pertamina Nugroho , Wahyu Kunto; Universitas Pertamina Wibowo , Aulia Rahma; Universitas Pertamina Annisa , Hanny Megawati; Universitas Pertamina Rosalinda
In communication between planes and satellites, Optical Beamforming Networks (OBFNs), which rely on many small and flat Phased Array Antennas (PAAs), need to be tuned in order to receive signals from specific angles. In this paper, we develop a deep neural network representation of tuning OBFNs. The problem of tuning an OBFN is in many aspects similar to training a deep neural network. We present a way to exploit the special structure of OBFNs into deep neural network and an algorithm for tuning OBFNs based on feedback that can be easily measured in real system. Training data, which consists of full signals, can be measured, and therefore is used in this paper. For pilot signals, the desired signal is known explicitly. Given the configuration of OBFNs and all nominal parameters required, it was verified in simulation that the deep neural network can be used to tune large scale OBFNs for any desired delays.
Volume: 16
Issue: 4
Page: 1607-1615
Publish at: 2018-08-01

Path Tracking on Autonomous Vehicle for Severe Maneuvre

10.12928/telkomnika.v16i4.9068
Zulkarnain; Universiti Teknologi Malaysia Zulkarnain , Hairi; Universiti Teknologi Malaysia Zamzuri , M. H. M.; Universiti Teknologi Malaysia Ariff , Umar Zakir Abdul; Universiti Teknologi Malaysia Hamid
Autonomous vehicle consists self-learning process consists recognizing environment, real time localization, path planning and motion tracking control. Path tracking is an important aspect on autonomous vehicle. The main purpose path tracking is the autonomous vehicle have an ability to follow the predefined path with zero steady state error. The non-linearity of the vehicle dynamic cause some difficulties in path tracking problems. This paper proposes a path tracking control for autonomous vehicle. The controller consists of a relationship between lateral error, longitudinal velocity, the heading error and the reference yaw rate. In addition, the yaw rate controller developed based on the vehicle and tyre model. The effectiveness of the proposed controller is demonstrated by a simulation.
Volume: 16
Issue: 4
Page: 1583-1589
Publish at: 2018-08-01

Significance of Speech Intelligibility Assessors in Medium Classroom Using Analytical Hierarchy Process

10.12928/telkomnika.v16i4.9043
Mokhtar; Universiti Teknologi Malaysia Skudai Harun , Khairunnisa Mohd; Universiti Teknologi Malaysia Skudai Yusof , Mohamad Ngasri; Universiti Teknologi Malaysia Skudai Dimon , Puspa Inayat; Universiti Teknologi Malaysia Skudai Khalid , Siti Zaleha; Universiti Teknologi Malaysia Skudai Abdul Hamid
When there are constraints on the resources-equipment, manpower and time-to conduct speech intelligibility tests, the most reliable or significant SI assessor for many different types of rooms is always sought for. The purpose of this study was to determine the most significant speech intelligibility assessor in four medium classrooms. The speech intelligibility assessors tested were RT60, C50, D50, and STIPA. The data were acquired by means of sound recorder that recorded six Malay words spoken by a trained male speaker, in four medium classrooms.The recorded speech signals were analyzed by DIRAC software. The data of four speech intelligibility assessors have to be normalized before it can be analyzed by AHP. In conclusion, C50 has shown the most consistent prediction of speech intelligibility in all sampled classrooms. On the other hand, as the room gets larger, RT60 becomes significant for determining speech intelligibility in these sampled classrooms.
Volume: 16
Issue: 4
Page: 1673-1678
Publish at: 2018-08-01

Design and Experimental Results of Universal Electric Vehicle Charger Using DSP

10.12928/telkomnika.v16i4.7308
Ali Saadon; Universiti Putra Malaysia Al-Ogaili , Ishak bin Aris; Universiti Putra Malaysia Aris , Mohammed Lutfi; Universiti Putra Malaysia Othman , Norhafiz; Universiti Putra Malaysia Azis , Dino; Universiti Putra Malaysia Isa , Yap; Universiti Putra Malaysia Hoon
Owing to the growing concerns over energy depletion and environmental issues around the world, more and more attention is given on replacing the fuel-based automobiles with electric vehicles (EVs) which have the characteristics of zero-emission and low noise. As a result, various countries have taken specific initiatives to de-carbonize their transport sectors by developing their own EV industry. Regardless of the environmental and economic benefits, substantial scales of grid-connected EVs impose incredible difficulties to the power grid. The main issues caused by EV charging to the power grid include harmonics, voltage drop, system instability, system losses and grid overloading. Therefore, this paper presents design and development of a novel method, which is by applying voltage-oriented control (VOC) algorithm in battery charging of electric bus.The power system of this work consists of three-phase PWM rectifier. The proposed method is based on mathematical analysis. Simulation and experimental works are performed to investigate behavior and performance of the proposed algorithm. This paperclearly described implementation of low and medium power laboratory prototype and operation of digital signal processor (DSP) via MATLAB / Simulink for the proposed method.
Volume: 16
Issue: 4
Page: 1435-1444
Publish at: 2018-08-01

The Development of Javanese Language Teaching Materials Through Introduction of Java Scripts Using Artificial Neural Network

10.12928/telkomnika.v16i4.8465
Siswo; Universitas Sultan Ageng Tirtayasa wardoyo , Kuntari; Universitas Sultan Ageng Tirtayasa W. , Anggoro S.; Universitas Sultan Ageng Tirtayasa Pramudyo , Suhendar; Universitas Sultan Ageng Tirtayasa Suhendar , Syarif; SMA Muhammadiyah 3 Yogyakarta Hidayat
The Java script is a traditional Indonesian scripts known as Hanacaraka or Carakan. Java script becomes less desirable students who have not been introduced by Master to students using interesting digital media. Javanese language teachers in teaching activities do not yet have interactive learning media in making Java script. This research aims to develop digital media recognition Java script using artificial neural network back propagation method as a teaching material of Java language. The sample of research used is basic java script which consist of 20 characters. The method of extraction properties used is Fast Fourier Transform, which is sampled horizontally and vertically. The result of this research showed FFT and ANN can be made of interactive learning media. The effectiveness of system with sensitivity value of 0,046 - 0,085, specification value 0,023 - 0,052, and system reliability is 59,5%. Validation value system that has been built for pattern recognition Java script on the training process is 100%, the testing process with the data -3o rotation, -1o, +1o, +3o reaches 100%, for a rotation -5o testing data, and +5° is 80%, testing of handwritten data is 65%, the test data +10o rotation is 25%, the test with the data translation is 5%, and for testing with the data and the data of rotation +90° zoom in (view) is 0%.
Volume: 16
Issue: 4
Page: 1697-1703
Publish at: 2018-08-01

Brain Tumor Detection Using Wathershed Segmentation Techniques and Area Calculation

10.11591/ijict.v7i2.pp71-76
Meenakshi Pareek , CK Jha , Saurabh Mukherjee , Chandani Joshi
This paper primarily focuses on to employ a novel approach to classify the brain tumor and its area. The Tumor is an uncontrolled enlargement of tissues in any portion of the human body. Tumors are of several types and have some different characteristics. According to their characteristics some of them are avoidable and some are unavoidable. Brain tumor is serious and life threatening issues now days, because of today’s hectic lifestyle. Medical imaging play important role to diagnose brain tumor .In this study an automated system has been proposed to detect and calculate the area of tumor. For proposed system the experiment carried out with 150 T1 weighted MRI images. The edge based segmentation, watershed segmentation has applied for tumor, and watershed segmentation has used to extract abnormal cells from the normal cells to get the tumor identification of involved and noninvolved areas so that the radiologist differentiate the affected area. The experiment result shows tumor extraction and area of tumor find the weather it is benign and malignant.
Volume: 7
Issue: 2
Page: 71-76
Publish at: 2018-08-01

Implementation of Artificial Neural Network Controller for Double-Input Boost Converter

10.11591/ijeecs.v11.i2.pp784-790
Yonis. M. Buswig , Al-Khalid bin Hj Othman , Norhuzaimin bin Julai , Sim Sy Yi , W. M. Utomo , A.J.M.S. Lim
This paper describes the design of an artificial neural network (ANN) control with power sharing control abilities of a new proposed double-input boost power converter (DIBC). The goal of this research is to model and design a high effectiveness and great performance double-input power converter for renewable energy applications. First, an artificial neural network controller design which is flexible versus a variable input voltage resource and variable load (to achieve the line regulation test and load regulation test) is proposed. Lastly, the suggested concept has been validated through experimentally on the laboratory prototype by using DSP TMS320F28335 real-time digital control. The experimental outcomes emphasize the authenticity of the suggested topology, which can be promising a novel topology that includes double-input power converter appropriate for renewable energy application systems.
Volume: 11
Issue: 2
Page: 784-790
Publish at: 2018-08-01

Meander bowtie Antenna for Wearable Application

10.12928/telkomnika.v16i4.9061
N.; Universiti Teknologi Malaysia Othman , N. A.; Universiti Teknologi Malaysia Samsuri , M. K. A.; Universiti Teknologi Malaysia Rahim , K.; Universiti Teknologi Malaysia Kamardin , H. A.; Universiti Tun Hussein Onn Malaysia Majid
This paper proposes a flexible compact bowtie antenna for medical application that operates at 2.45 GHz. The proposed antennas are miniaturized using meander technique. Both substrates and conducting material of the antenna are made of flexible material semi-transparent film as the substrate and shieldit fabric as the conducting material which suitable for wearable and on body application. The results show that the total length of the antenna is significantly reduced by up to 38%. However, the gain of the antenna is slightly decreased when the size of the antenna become smaller. The results of this research could provide guidance and has significant implication for future development of wearable electronics especially in medical monitoring application.
Volume: 16
Issue: 4
Page: 1522-1526
Publish at: 2018-08-01

Characteristics MIMO 2x4 Antenna for 5G Communication System

10.12928/telkomnika.v16i4.8377
Yusnita; Universitas Riau Rahayu , Jodi; Universitas Riau Wijaya , Elsa; Universitas Riau Syafitri
This paper presents the characteristic MIMO 2x4 antenna for 5G communication system. The proposed antenna works at 28 GHz and simulated by using CST simulation software. The antenna uses RT Duroid 5880 substrate with dielectric constant of 2.2. The MIMO antenna consists of eight elements with rectangular patches and inset feeding. The dimension of patch (Wp x Lp) is 6 mm x 8 mm. There are three (3) antenna configurations derived in this paper such as; single element, 1x4 elements and 2x4 elements. The MIMO 1x4 elements antenna configuration is designed based on the single element antenna with the distance between center to center elements antennas of 5 mm. The MIMO 2x4 antenna is formed from the MIMO 1x4 element configuration with the opposite direction. The 2x4 element antenna, a distance between opposite antenna elements is 10 mm. From the simulation results, it is shown that by increasing the number elements of antenna affect to the directivity and the return loss. Antenna with 2x4 elements has 14 dBi of directivity with the return loss of -19 dB. While antenna with 1x4 elements, the directivity obtained is 14.3 dBi with return loss of -18 dB.
Volume: 16
Issue: 4
Page: 1508-1514
Publish at: 2018-08-01

Non-Contact Capacitive Technique for Biomass Flow Sensing

10.11591/ijeecs.v11.i2.pp531-541
Rumana Tasnim , Sheroz Khan , Atika Arshad , Molla Rashied Hussein
To facilitate real-time flow measurement, this paper aims to realize biomass flow sensing through electronic non-contact capacitive means. Hardware implementation has been carried out using a modified OP-AMP-based bridge circuit, with one arm made of a standard capacitance while the other arm is made from two specifically designed capacitive electrodes fitted on a piping system sensing biomass flow. The experimental results are targeted to obtain data for given biomass types through a custom-developed biomass flow piping system. Several flow affecting parameters namely: electrodes’ shapes, the location of electrodes on the piping system, biomass material type, and particle size have been considered in obtaining experimental data. Also, the circuit has been simulated to analyze flow sensing behavior for the proposed technique by evaluating the measurement data and assessing conformity between experimentally obtained and simulated data.
Volume: 11
Issue: 2
Page: 531-541
Publish at: 2018-08-01

Controlling a DC Motor through Lypaunov-like Functions and SAB Technique

10.11591/ijece.v8i4.pp2180-2198
Alejandro Rincón , Fabiola Angulo , Fredy Hoyos
In this paper, state adaptive backstepping and Lyapunov-like function methods are used to design a robust adaptive controller for a DC motor. The output to be controlled is the motor speed. It is assumed that the load torque and inertia moment exhibit unknown but bounded time-varying behavior, and that the measurement of the motor speed and motor current are corrupted by noise. The controller is implemented in a Rapid Control Prototyping system based on Digital Signal Processing for dSPACE platform and experimental results agree with theory.
Volume: 8
Issue: 4
Page: 2180-2198
Publish at: 2018-08-01

Cost implication of Line Voltage variation on Three Phase Induction Motor operation

10.12928/telkomnika.v16i4.9628
Aderibigbe Israel; Covenant University Adekitan , Bukola; Covenant Universit Adetokun , Tobi; Covenant University Shomefun , Alex; Covenant University Aligbe
Globally, there is a drive toward ensuring energy efficiency in all aspect of production operations and power supply systems. Industries are the backbone of our modern word, and a significant percentage of industrial operations are motor driven. Three Phase Induction Motor is massively deployed in industries due to its ruggedness, reasonable cost and ease of maintenance. The energy efficiency of the induction motor is affected by the internal configurations of the motor and the nature of the supply. Power supply fluctuations result in power quality issues and its attendant negative effects on equipment operation. This research, studies the cost and performance implication of the effects of balanced over voltage, balanced voltage, balanced under voltage and unbalance voltage on the operation of the three phase induction motor using the peculiarities of Nigeria. The result shows that, there is an increase in operational cost due to increased energy loss in the windings as a result of voltage variations from the balanced state, with balanced over voltage operation showing more cost severity among the voltage variations considered.
Volume: 16
Issue: 4
Page: 1404-1412
Publish at: 2018-08-01

Coal-Fired Boiler Fault Prediction using Artificial Neural Networks

10.11591/ijece.v8i4.pp2486-2493
Nong Nurnie Mohd Nistah , King Hann Lim , Lenin Gopal , Firas Basim Ismail Alnaimi
Boiler fault is a critical issue in a coal-fired power plant due to its high temperature and high pressure characteristics. The complexity of boiler design increases the difficulty of fault investigation in a quick moment to avoid long duration shut-down. In this paper, a boiler fault prediction model is proposed using artificial neural network. The key influential parameters analysis is carried out to identify its correlation with the performance of the boiler. The prediction model is developed to achieve the least misclassification rate and mean squared error. Artificial neural network is trained using a set of boiler operational parameters. Subsequenlty, the trained model is used to validate its prediction accuracy against actual fault value from a collected real plant data. With reference to the study and test results, two set of initial weights have been tested to verify the repeatability of the correct prediction. The results show that the artificial neural network implemented is able to provide an average of above 92% prediction rate of accuracy.
Volume: 8
Issue: 4
Page: 2486-2493
Publish at: 2018-08-01

Optimizing Laying Hen Diet using Multi-Swarm Particle Swarm Optimization

10.12928/telkomnika.v16i4.7765
Gusti Ahmad Fanshuri; Universitas Brawijaya Alfarisy , Wayan Firdaus; Universitas Brawijaya Mahmudy , Muhammad Halim; Universitas Brawijaya Natsir
Formulating animal diet by accounting fluctuating cost, nutrient requirement, balanced amino acids, and maximum composition simultaneously is a difficult and complex task. Manual formulation and Linear Programming encounter difficulty to solve this problem. Furthermore, the complexity of laying hen diet problem is change through ingredient choices. Thus, an advanced technique to enhance formula quality is a vital necessity. This paper proposes the Multi-Swarm Particle Swarm Optimization (MSPSO) to enhance the diversity of particles and prevent premature convergence in PSO. MSPSO work cooperatively and competitively to optimize laying hen diet and produce improved and stable formula than Genetic Algorithm, Hybridization of Adaptive Genetic Algorithm and Simulated Annealing, and Standard Particle Swarm Optimization with less time complexity. In addition, swarm size, iteration, and inertia weight parameters are investigated and show that swarm size of 50 for each sub-swarm, total iteration of 16,000, and inertia weight of 6.0 should be used as a good parameter for MSPSO to optimize laying hen diet.
Volume: 16
Issue: 4
Page: 1712-1723
Publish at: 2018-08-01
1 2 3
...
2012 2013
Show 1439 of 2013

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