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

31,456 Article Results

Design of smart wireless changeover for continuous electric current feeding from power sources of variable capacities

10.11591/ijece.v10i4.pp3460-3467
Haider A. H. Alobaidy , Hikmat N. Abdullah , Tariq M. Salman
Electric power has become a vital element for life today. Despite this importance, electric power consumers in Iraq suffer from the problem of noncontinuity and daily electric power supply interruption. This problem led to the use of various sources of electric power as an alternative to compensate for the shortage of electric power provided by the Iraqi national grid. In this work, a smart wireless changeover device is designed using wireless sensor networks technology aiming to solve problem caused by the multiplicity of power sources received at home and governmental buildings in Iraq by controlling operation of some electrical devices (which consume high current) in the home or workplace automatically when changing source of electricity from one to another. This solution will help to ensure the continuity of electric current feeding from power sources of variable capacities, also, to rationalize power consumption by assigning an operation priority to electric devices. Furthermore, a statistical measurement as a case study was performed in a building with a total power consumption of 160.8 KW/h. The result showed that the device functions effectively and it is capable of achieving an average saving in power of about 50% to 86% depending on the applied priorities and case study scenario.
Volume: 10
Issue: 4
Page: 3460-3467
Publish at: 2020-08-01

Enhancement of student performance prediction using modified K-nearest neighbor

10.12928/telkomnika.v18i4.13849
Saja; Iraqi Commission for Computers & Informatics (IIPS-ICCI) Taha Ahmed , Rafah; Iraqi Commission for Computers & Informatics (IIPS-ICCI) Al-Hamdani , Muayad; University of Technology Baghdad Sadik Croock
The traditional K-nearest neighbor (KNN) algorithm uses an exhaustive search for a complete training set to predict a single test sample. This procedure can slow down the system to consume more time for huge datasets. The selection of classes for a new sample depends on a simple majority voting system that does not reflect the various significance of different samples (i.e. ignoring the similarities among samples). It also leads to a misclassification problem due to the occurrence of a double majority class. In reference to the above-mentioned issues, this work adopts a combination of moment descriptor and KNN to optimize the sample selection. This is done based on the fact that classifying the training samples before the searching actually takes place can speed up and improve the predictive performance of the nearest neighbor. The proposed method can be called as fast KNN (FKNN). The experimental results show that the proposed FKNN method decreases original KNN consuming time within a range of (75.4%) to (90.25%), and improve the classification accuracy percentage in the range from (20%) to (36.3%) utilizing three types of student datasets to predict whether the student can pass or fail the exam automatically.
Volume: 18
Issue: 4
Page: 1777-1783
Publish at: 2020-08-01

Texture classification of fabric defects using machine learning

10.11591/ijece.v10i4.pp4390-4399
Yassine Ben Salem , Mohamed Naceur Abdelkrim
In this paper, a novel algorithm for automatic fabric defect classification was proposed, based on the combination of a texture analysis method and a support vector machine SVM. Three texture methods were used and compared, GLCM, LBP, and LPQ. They were combined with SVM’s classifier. The system has been tested using TILDA database. A comparative study of the performance and the running time of the three methods was carried out. The obtained results are interesting and show that LBP is the best method for recognition and classification and it proves that the SVM is a suitable classifier for such problems. We demonstrate that some defects are easier to classify than others.
Volume: 10
Issue: 4
Page: 4390-4399
Publish at: 2020-08-01

Random forest application on cognitive level classification of E-learning content

10.11591/ijece.v10i4.pp4372-4380
Benny Thomas , Chandra J.
The e-learning is the primary method of learning for most learners after the regular academics studies. The knowledge delivery through e-learning technologies increased exponentially over the years because of the advancement in internet and e-learning technologies. Knowledge delivery to some people would never have been possible without the e-learning technologies. Most of the working professional do focused studies for carrier advancement, promotion or to improve the domain knowledge. These learner can find many free e-learning web sites from the internet easily in the domain of interest. However it is quite difficult to find the best e-learning content suitable for their learning based on their domain knowledge level. User spent most of the time figuring out the right content from a plethora of available content and end up learning nothing. An intelligent framework using machine learning algorithms with Random Forest Classifier is proposed to address this issue, which classifies the e-learning content based on its difficulty levels and provide the learner the best content suitable based on the knowledge level .The frame work is trained with the data set collected from multiple popular e-learning web sites. The model is tested with real time e-learning web sites links and found that the e-contents in the web sites are recommended to the user based on its difficulty levels as beginner level, intermediate level and advanced level.
Volume: 10
Issue: 4
Page: 4372-4380
Publish at: 2020-08-01

A review of microstrip antenna designs for TV white space applications

10.11591/ijeecs.v19.i2.pp855-863
Chamath Kalanaka Vithanawasam , Yi Lung Then , Hieng Tiong Su
A review on prominent microstrip antennas fabricated for TV White Space applications is presented. This paper will delve into some of the most notable microstrip antenna designs in this frequency band that have come up in recent years. They will be analyzed to identify their strengths and weaknesses, and feedback is provided on their perceived usefulness. These antennas are designed with specific intentions, such as being placed in areas prone to harsh weather, or for long distance communications. One of the most recent antenna types to enter mainstream discussion is the microstrip patch antenna, which can easily be altered to fit various applications. Methods of connectivity such as TV White Space are enthusiastically used in various applications pertaining to connectivity and various microstrip antennas have been designed for this purpose. A conclusion was reached on the compact shorted printed monopole antenna being the most plausible choice from the antennas that have been considered and discussed.
Volume: 19
Issue: 2
Page: 855-863
Publish at: 2020-08-01

Performance enhancement of DC/DC converters for solar powered EV

10.11591/ijece.v10i4.pp3423-3430
Nagaraj S. , Ranihemamalini R. , Rajaji L.
The paper initially presents the essential drive arrangement required for electric vehicle. It requests high power bidirectional stream ability, with wide info voltage range, and yield voltage of vitality stockpiling gadgets, for example, super capacitors or batteries shift with the adjustment in stack. At that point the tenacity and outline of previously mentioned converter is proposed in this paper. The converter which relates a half extension topology, has high power stream ability and least gadget focuses on that can appropriately interface a super capacitor with the drive prepare of a crossover electric vehicle. Besides, by contrasting the fundamental qualities and applications with some ordinary bidirectional DC/DC converter, the proposed converter has low gadget rating and can be controlled by obligation cycle and stage move. Finally, the most essential attributes of this converter is that it utilizes the transformer spillage inductance as the essential vitality exchange component and control parameters, Simulation waveforms in light of MATLAB recreation are given to exhibit the integrity of this novel topology, and this converter is additionally reasonable for high power application, specifically to control the charge-release of super capacitors or batteries that can be utilized as a part of cross breed solar based electric vehicle.
Volume: 10
Issue: 4
Page: 3423-3430
Publish at: 2020-08-01

Offset effect on the S-Bend structure losses and optimization of its size for integrated optics

10.11591/ijece.v10i4.pp4162-4167
Fatima Brik , S. Harize , A. Fares , K. Saouchi
The S-Bend structures are heavily exploited to join optical components. Reducing the power loss caused by the curve is the main objective in the design step of these components. However integrated optical circuits require S-Bend waveguide to be low loss and compact sized. In this paper, we present a contribution to link the curved structure to the straight waveguide by using the simulated bend function available in the Beam propagation tool of the Rsoft commercial software package. Simulation results confirm that this approach allows a reduction of the size of the curved structure with offset with relatively minimum of losses for photonic field.
Volume: 10
Issue: 4
Page: 4162-4167
Publish at: 2020-08-01

GWO-based estimation of input-output parameters of thermal power plants

10.12928/telkomnika.v18i4.12957
Osea; University of Lampung Zebua , I Made; University of Mataram Ginarsa , I Made; University of Mataram Ari Nrartha
The fuel cost curve of thermal generators was very important in the calculation of economic dispatch and optimal power flow. Temperature and aging could make changes to fuel cost curve so curve estimation need to be done periodically. The accuracy of the curve parameters estimation strongly affected the calculation of the dispatch. This paper aims to estimate the fuel cost curve parameters by using the grey wolf optimizer method. The problem of curve parameter estimation was made as an optimization problem. The objective function to be minimized was the total number of absolute error or the difference between the actual value and the estimated value of the fuel cost function. The estimated values of parameter that produce the smallest total absolute error were the values of final solution. The simulation results showed that parameter estimation using gray wolf optimizer method further minimized the value of objective function. By using three models of fuel cost curve and given test data, parameter estimation using grey wolf optimizer method produced the better estimation results than those estimation results obtained using least square error, particle swarm optimization, genetic algorithm, artificial bee colony and cuckoo search methods.
Volume: 18
Issue: 4
Page: 2235-2244
Publish at: 2020-08-01

Adaptive management of technical condition of power transformers

10.11591/ijece.v10i4.pp3862-3868
Vladimir M. Levin , Ammar A. Yahya
Ensuring reliable operation of power transformers as part of electric power facilities is assigned to the maintenance and repair system, whose important components are diagnostics and monitoring of the technical condition. Monitoring allows you to answer the question of whether the transformer abnormalities and how to do they manifest, while diagnostics allow determining the nature, the severity of the problem, determine the cause and possible consequences. The article presents the results of the authors ' research on creating an algorithm for adaptive control of the technical condition of power transformers using diagnostic and monitoring data. The developed algorithm implements the decision-making procedure for ensuring the reliable operation of oil-filled transformer equipment as part of the substations of electric power facilities. The decision-making procedure is based on the method of statistical Bayesian identification the states of a transformer based on the results of dissolved gas analysis (DGA) in oil. The method is characterized by high reliability of recognizing defects in the transformer and the ability to adapt the probabilities of the obtained solutions to the newly received diagnostic information. These results illustrate the effectiveness of the developed approach and the possibility of its application in the operation of oil-filled transformer equipment.
Volume: 10
Issue: 4
Page: 3862-3868
Publish at: 2020-08-01

Analysis sentiment about islamophobia when Christchurch attack on social media

10.12928/telkomnika.v18i4.14179
Windu; STMIK Nusa Mandiri Jakarta Gata , Achmad; STMIK Nusa Mandiri Jakarta Bayhaqy
Islamophobia is formed by "Islam" with "-phobia" which means "fear of Islam". This shows the view of Islam as "other" and can threaten Western culture. The recent horrific terror attack that took place at the Christchurch mosque in New Zealand, is the result of allowing an attitude of hatred towards Islam in the West. Twitter is social media that allows users send real-time messages and can be used for sentiment analysis because it has a large amount of data. The lexical based method using VADER is used for automatic labeling of crawling data from Twitter. And then compare Supervised Machine Learning Naïve Bayes and SVM algorithm. Addition of SMOTE for Imbalanced Data. As result, SVM with SMOTE is proven the highest performance value and short processing time.
Volume: 18
Issue: 4
Page: 1819-1827
Publish at: 2020-08-01

A comparison of single phase standalone square waveform solar inverter topologies: half bridge and full bridge

10.11591/ijece.v10i4.pp3384-3392
Aicha Chemseddine , Noureddine Benabadji , Ali Cheknane , Salah Eddine Mankour
In stand-alone photovoltaic installations the photovoltaic inverter allows transforming the DC power produced by the photovoltaic modules into an AC power. Depending on the shape of the AC output voltage generated by the inverter there exist three main types of stand-alone PV inverters: pure sine waveform inverters, modulated sine waveform inverters and square waveform inverters and each type of these inverters is also divided into different topologies. In this paper we will be interested and study the square waveform stand-alone inverter topologies which are the half bridge and the full-bridge inverter topologies.
Volume: 10
Issue: 4
Page: 3384-3392
Publish at: 2020-08-01

A new fast efficient non-maximum suppression algorithm based on image segmentation

10.11591/ijeecs.v19.i2.pp1062-1070
Oday Jasim Al-Furaiji , Nguyen Anh Tuan , Viktar Yurevich Tsviatkou
In this paper, the problem of finding local extrema in grayscale images is considered. The known non-maximum suppression algorithms provide high speed, but only single-pixel extrema are extracted, skipping regions formed by multi-pixel extrema. Morphological algorithms allow toextract all extrema but its maxima and minima are processed separately with high computational complexity by iterative processing based on image reconstruction using image morphological dilation and erosion. In this paper a new fast efficient non-maximum suppression algorithm based on image segmentation and border analysis is proposed. The proposed algorithm considers homogeneous areas, which are formed by multi-pixel extrema and are the local maxima or minima in relation to adjacent areas, eliminating iterative processing of non-extreme pixels and assigning label numbers to local extrema during their search. The proposed algorithm allowed to increase the accuracy of local extremum extraction in comparison with known non-maximum suppression algorithms and reduce the computational complexity and the use of RAM in comparison with the morphological algorithms.
Volume: 19
Issue: 2
Page: 1062-1070
Publish at: 2020-08-01

Image transmission using visible light communication in data communication

10.12928/telkomnika.v18i4.14892
Alfajri; Universitas Telkom Tsaqifurrosyid , Mia; Universitas Telkom Rosmiati , Moch. Fachru; Universitas Telkom Rizal
The development of network communication technology is currently developing rapidly, one of which is the use of LED lights that are not only used as lighting in the room but can also be used as a medium of data communication between users through light media. VLC is the latest innovation in the field of data communication that is currently being developed where the process of sending data used light media.. The simulation  of sending data using VLC can be done on the transmitter and receiver side by using Visual Studio application as an application that can visualize the process of sending data. By using this system the process of sending data every bit from transmiiter to the receiver can be seen so that the success rate of sending data can be easily seen by the user. system used arduino Uno as microprocessor. From the test results obtained the success rate of displaying images sent by the transmitter is 100% with a maximum distance of 50 cm with an image capacity of 20 KB with a delivery time of approximately 30 minutes.
Volume: 18
Issue: 4
Page: 1771-1776
Publish at: 2020-08-01

Single document keywords extraction in Bahasa Indonesia using phrase chunking

10.12928/telkomnika.v18i4.14389
I Nyoman Prayana; Universitas Gadjah Mada Trisna , Arif; Universitas Gadjah Mada Nurwidyantoro
Keywords help readers to understand the idea of a document quickly. Unfortunately, considerable time and effort are often needed to come up with a good set of keywords manually. This research focused on generating keywords from a document automatically using phrase chunking. Firstly, we collected part of speech patterns from a collection of documents. Secondly, we used those patterns to extract candidate keywords from the abstract and the content of a document. Finally, keywords are selected from the candidates based on the number of words in the keyword phrases and some scenarios involving candidate reduction and sorting. We evaluated the result of each scenario using precision, recall, and F-measure. The experiment results show: i) shorter-phrase keywords with string reduction extracted from the abstract and sorted by frequency provides the highest score, ii) in every proposed scenario, extracting keywords using the abstract always presents a better result, iii) using shorter-phrase patterns in keywords extraction gives better score in comparison to using all phrase patterns, iv) sorting scenarios based on the multiplication of candidate frequencies and the weight of the phrase patterns offer better results.
Volume: 18
Issue: 4
Page: 1917-1925
Publish at: 2020-08-01

Semantics-based clustering approach for similar research area detection

10.12928/telkomnika.v18i4.15001
Marion Oluwabunmi; Landmark University Omu Aran Adebiyi , Emmanuel B.; Covenant University Ota Adigun , Roseline Oluwaseun; Landmark University Omu Aran Ogundokun , Abidemi Emmanuel; Landmark University Omu Aran Adeniyi , Peace; Landmark University Omu Aran Ayegba , Olufunke O.; Covenant University Ota Oladipupo
The manual process of searching out individuals in an already existing research field is cumbersome and time-consuming. Prominent and rookie researchers alike are predisposed to seek existing research publications in a research field of interest before coming up with a thesis. From extant literature, automated similar research area detection systems have been developed to solve this problem. However, most of them use keyword-matching techniques, which do not sufficiently capture the implicit semantics of keywords thereby leaving out some research articles. In this study, we propose the use of Ontology-based pre-processing, Latent Semantic Indexing and K-Means Clustering to develop a prototype similar research area detection system, that can be used to determine similar research domain publications. Our proposed system solves the challenge of high dimensionality and data sparsity faced by the traditional document clustering technique. Our system is evaluated with randomly selected publications from faculties in Nigerian universities and results show that the integration of ontologies in preprocessing provides more accurate clustering results.
Volume: 18
Issue: 4
Page: 1874-1883
Publish at: 2020-08-01
1 2 3
...
2097 2098
Show 1209 of 2098

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