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

31,458 Article Results

A comparative study of deep learning based language representation learning models

10.11591/ijeecs.v22.i2.pp1032-1040
Mohammed Boukabous , Mostafa Azizi
Deep learning (DL) approaches use various processing layers to learn hierarchical representations of data. Recently, many methods and designs of natural language processing (NLP) models have shown significant development, especially in text mining and analysis. For learning vector-space representations of text, there are famous models like Word2vec, GloVe, and fastText. In fact, NLP took a big step forward when BERT and recently GTP-3 came out. In this paper, we highlight the most important language representation learning models in NLP and provide an insight of their evolution. We also summarize, compare and contrast these different models on sentiment analysis, and thus discuss their main strengths and limitations. Our obtained results show that BERT is the best language representation learning model.
Volume: 22
Issue: 2
Page: 1032-1040
Publish at: 2021-05-01

Software aging prediction and rejuvenation in cloud computing environment: a new approach

10.11591/ijeecs.v22.i2.pp1006-1012
Shruthi P , Nagaraj G Cholli
Service availability is one of the major requirements for user satisfaction. Several researches were conducted in recent years to find suitable infrastructure to enhance the availability. Even though both hardware and software are to be in good condition, in recent years, software faults are the major concern for service availability. Software aging is a type of software fault. Software aging occurs as a result of errors accumulation in the internal environment of the system leading to performance degradation. To manage software aging, technique used is software rejuvenation. There exist two kinds of approaches for studying software aging and deriving optimal software rejuvenation schedules. The two approaches are measurement based and model based. In model based approach, analytic models are built for capturing system degradation and rejuvenation process. In measurement based approach, attributes are periodically monitored and that may indicate signs of software aging. In this work, a prototype of measurement based model has been developed. The model captures the aging indicator metrics from cloud environment and rejuvenates once the system reaches aged status. The proposed model uses platform independent, non-intrusive technique for capturing metrics. The rejuvenation carried out after analysing the captured metrics, increases the availability of the service.
Volume: 22
Issue: 2
Page: 1006-1012
Publish at: 2021-05-01

On active anti-islanding techniques: survey

10.11591/ijeecs.v22.i2.pp609-618
Yasser Ahmed Elshrief , Sameh Abd-Elhaleem , Belal Abo Zalam , Amin D. Asham
The phenomenon of feeding loads from any distributed generators (DGs) with a total disconnection of utility grid at the point of common coupling is called Islanding. The DGs are usually independently controlled. Hence, when the islanding problem occurs, the electric utility loses the control and supervision over that section of the power grid. Furthermore, prolonged islanding can prevent reconnection to the power grid and may cause damage due to voltage and frequency excursions. Therefore, the islanding detection, which is also called anti-islanding (AI), is one of the most critical aspects of the integration of DG sources into the power grid. In this paper, a comprehensive survey on the local AI techniques is illustrated, especially active type which is used for improving the performance regarding the size of the non-detection zone and detection speed. Extensive comparisons are provided to demonstrate the effectiveness of each technique.
Volume: 22
Issue: 2
Page: 609-618
Publish at: 2021-05-01

Network analysis of Youtube videos based on keyword search with graph centrality approach

10.11591/ijeecs.v22.i2.pp780-786
Edi Surya Negara , Ria Andryani , Riyan Amanda
Youtube is a social media that has billions of users, with this can be used as a promotional media, trends, business, and so forth. This study aims to analyze the correlation between Youtube videos by utilizing hashtags on video using graph theory. Data collection in this study uses scraping techniques taken from the Youtube website in the form of links, titles, keywords, and hashtags. The method used in this research is Social Network Analysis, the measurements used in this study are degree centrality and betweenness centrality. The results of this study indicate that the most popular hashtags with the keyword search for "viruses" are #KidflixPT, #Portugues, and #Mondo with degree centrality values equal to 0.071875. and the correlation between the most closely related videos about #Coronavirus with a value of betweenness centrality of 0.082626.
Volume: 22
Issue: 2
Page: 780-786
Publish at: 2021-05-01

A review of codebook design methods for sparse code multiple access

10.11591/ijeecs.v22.i2.pp927-935
Syed Aamer Hussain , Norulhusna Ahmad , Ibraheem Shayea , Hazilah Mad Kaidi , Liza Abdul Latiff , Norliza Mohamed , Suriani Mohd Sam
The progressions in telecommunication beyond the 5th generation have created a need to improve research drifts. The current 5G study has an important focus on non-orthogonal multiple access (NOMA) technology. sparse code multiple access (SCMA) is a promising technique within NOMA, enhancing the multi-user handling capability of next-generation communication. In the SCMA sphere, codebook designing and optimisation are essential research matters. This study conversed with different codebook design practises existing in the literature, analysing them for numerous parameters, including bit error rate (BER), an optimisation technique, and channel settings. From the analysis, the paper presents the efficiency of different approaches. The article also discusses the prospects and challenges of SCMA optimisation in practical implementation in various domains.
Volume: 22
Issue: 2
Page: 927-935
Publish at: 2021-05-01

Hybrid NRZ/RZ line coding scheme based hybrid FSO/FO dual channel communication systems

10.11591/ijeecs.v22.i2.pp866-873
Mahmoud M. A. Eid , Ahmed Nabih zaki Rashed
This study simulates the hybrid non return to zero (NRZ)/return to zero (RZ) line coding scheme based hybrid free space optics (FSO)/fiber optics (FO) dual channel communication systems. The max Q factor/Min BER are simulated after APD receiver based both erbium doped fiber amplifiers (EDFAs) and wide band traveling wave semiconductor optical amplifiers (WBTWSOAs) with 50 km fiber channel and 4 km FSO channel. Max SPAL/min noise SPAL, max signal power amplitude/min noise signal power variations with spectral frequency, and the total electrical power are demonstrated and clarified in this proposed study. This work emphasized that the fiber channel is reached up to 100 km reach and FSO channel can be also extended to 4 km reach with 40 Gbps.
Volume: 22
Issue: 2
Page: 866-873
Publish at: 2021-05-01

Development of an IoT-based water and power monitoring system for residential building

10.11591/ijeecs.v22.i2.pp744-751
Leah Santos , John Carlo Bautista , Matt William Estanque , Christian John Paloa , Ana Beatrice Villaran
This study provides information between tenants and landlords on the use of the Internet of Things for power and water monitoring systems. It is one way to make reading meters and water meters easier to access using the available internet connection. The developed application using the android studio software is installed on a smartphone/tablet and verified to fully working on android versions from 4.1 (jellybean) to android 9.0 (pie). Tests were carried out in a household where the prototype was installed in a residential apartment. The data collected was monitored in the application and viewed by tenants and landlords. The results from the mean comparison of the power and volume readings measured by the wattmeter and water meter claim that the readings from the conventional meters and designed prototype have no significant difference using the Mann-Whitney U test. Evaluations were conducted showing that the device and the developed application using IoT is reliable, accurate, functional and user-friendly to use by tenants and landlords.
Volume: 22
Issue: 2
Page: 744-751
Publish at: 2021-05-01

Exploiting non-orthogonal multiple access in device-to-device communication

10.11591/ijeecs.v22.i2.pp919-926
Sang Hoon Lee , Soo Young Shin
This paper proposes an uplink non-orthogonal multiple access (NOMA) system with device-to-device (D2D) communication, enabling NOMA users to communicate with other users/devices using D2D communication to improve the system capacity. In the NOMA-D2D system, two cellular users communicated with the BS using uplink NOMA, and two cellular users simultaneously communicated with the D2D users using downlink NOMA. Closed-form solutions for the ergodic sum capacity of the proposed system are derived analytically. The analytical results are validated via simulations and they are compared with the results obtained from conventional schemes. The comparison shows that, in scenarios where efficient interference cancellation can be achieved, the proposed NOMA system with the D2D model can achieve higher capacity gains than conventional benchmark schemes. When  dB, NOMA-D2D achieves capacity gains of 192.2% and 157.5% over the conventional OMA and the time-sharing-based NOMA, respectively.
Volume: 22
Issue: 2
Page: 919-926
Publish at: 2021-05-01

Frequency response analysis of dielectric materials in a parallel-plate transmission line

10.11591/ijeecs.v22.i2.pp893-901
Aaron Don Munsayac Africa , Gregory James Pe , Robert Ianny Roy Quijano
A transmission line allows different frequencies to conduct alternating current (AC). They are a peculiar type of wire that allows signal transmission while making it resistant to external noises. A parallel-plate transmission line is a type of transmission line designed with two parallel plates with a dielectric sheet material in the center, as the name implies. The parallel-plate transmission lines are usually used for a miniature setup in which the line prevents the signal from losing power. However, the line's frequency response is a varying setup in which a change in a parameter can fully change the frequency response of the line, and in turn trigger inefficiency. With this, different factors such as the conductor, the size, and the dielectric material of the parallel-plate transmission line can affect its frequency response. Specifically, the analysis of the transmission would test the various frequency responses when the dielectric sheet content is varied. The researchers will carry out experiments on air, Teflon, plexiglass, and E type glass dielectrics.
Volume: 22
Issue: 2
Page: 893-901
Publish at: 2021-05-01

Data communication for drone-enabled internet of things

10.11591/ijeecs.v22.i2.pp1216-1222
Yousra Abdul Alsahib S. Aldeen , Haider Mohammed Abdulhadi
Internet of things (IoT) is one of the prominent emerged technology of interconnected devices for people convenient and smart services. Recent advancement in this area caused various new challenges especially deployment of infrastructure. In order to fulfill the network requirements, the dynamic and dedicated drone networks have designed as a cost effective and flexible solution. The technologies of IoT and drone are emerged to collect, forward the data for further process. Data communication among drones and IoT infrastructure is new area of research where various different existing protocol are used. However, still this area need attention due to mobility of drones, obstacles and interferences in these networks. This paper proposes a Drone enabled Data Communication for Internet of Things (DDC-IoT) as a data communication solution for IoT networks, data collection centers and drones. The proposed data commination solution is tested in simulation to analyze its performance especially for real time critical applications in terms of data throughput and data delay.
Volume: 22
Issue: 2
Page: 1216-1222
Publish at: 2021-05-01

Dual-band bandpass filter based on two U-shaped defected microstrip structure

10.11591/ijeecs.v22.i2.pp909-918
Mussa Mabrok , Zahriladha Zakaria , Yully Masrukin , Tole Sutikno
This paper presents design of dual-band bandpass filter by integrating conventional quarter-wavelength short circuit stubs bandpass filter with U-shaped defected microstrip structure notch filter. Based on the parametric analysis, it is found that high attenuation level can be achieved by using two U-shaped defected microstrip structure separated by specific distance. The designed circuit simulated using advanced design system and fabricated based on Roger 4350B. The simulation results are in good agreement with measured results. The designed filter covered two pass bands centered at 2.51 GHz and 3.59 GHz with 3-dB fractional bandwidth of 15.94% and 15.86%, respectively, return losses better than 15 dB, and insertion losses better than 1 dB. The designed device can be used for wireless communication applications such as WLAN and WiMAX.
Volume: 22
Issue: 2
Page: 909-918
Publish at: 2021-05-01

An efficient NSCE algorithm for multi-objective reactive power system compensation with UPFC

10.11591/ijeecs.v22.i2.pp648-659
Messaoud Belazzoug , Abdallah Chanane , Karim Sebaa
This paper proposes a novel approach based on the NSCE (elitist non dominated sorting cross entropy), for the optimization of the location and the size of a flexible AC transmission system device (FACTS) namely: unified power flow controller (UPFC) to achieve the optimal reactive power flow (ORPF). In the present work, the main objective is to minimize the real power losses, the cost investment of several UPFC and the deviation voltages using intelligent algorithms. The proposed study is multiobjective, in which, the power generator buses, the control voltages, the ratio tap changer of transformers and the reactive power injections from installed UPFC are considered as control variables. The proposed NSCE algorithm is validated on IEEE 30-bus test system. A comparison with elitist non dominated sorting genetic algorithm (NSGA-II) and a regularity model-based multiobjective estimation of distribution algorithm (RM-MEDA) is done and completed with hybridization of them.
Volume: 22
Issue: 2
Page: 648-659
Publish at: 2021-05-01

Validation test on 3d heart phantom for mitral valve leaflet tracking

10.11591/ijeecs.v22.i2.pp717-725
Lina Farhana Mahadi , Nabilah Ibrahim , Shahnoor Shanta , Hideyuki Hasegawa
Mitral valve movement is essential to be identified in order to monitor the abnormality of blood flow in right side of heart. The estimation and tracking of mitral valve has seldom been investigated since it required high temporal rate to scan the echocardiography images and it depends on the operator to capture the low-speckle and-noise images. This study presents the validation experiment performed on heart phantom made of thermoplastic polyurethane (TPU) filament which the objective is to validate the previous features tracking technique implemented in mitral valve locating in video frames using Kanade-Lucas-Tomasi (KLT) algorithm. The outcome was able to automatically detect the edge of mitral valve and thus in future, it manages to predict the flowing of blood pattern. An in-vitro experiment was conducted which involved a valve phantom scanning in water tank that connected to water pump. It was found in this study that the technique capable to detect and visualize the mitral valve up to 59 frames in 2.36 secondsby tracking the features of minimum eigenvalue within the selected region. It was also produced a good agreement of valve distance between the true value and the measured one, which achieved the minimum of 88% similarity. This yielded the validation of the proposed technique to track and visualize the mitral valves.
Volume: 22
Issue: 2
Page: 717-725
Publish at: 2021-05-01

Improvement of power transfer efficiency of hexagonal coil arrays in misalignment conditions

10.11591/ijeecs.v22.i2.pp638-647
Sianturi Tigor Franky Devano , Taufik Hidayat , Mudrik Alaydrus
Wireless charging by transferring energy between two objects using electromagnetic fields commonly called Wireless power transfer is an alternative technology that is physically installed in an electric vehicle (EV) to charge. Parking alignment is a very important factor in driver behavior that affects Power transfer efficiency (PTE). The proposed hexagonal coil array design in this experiment is to optimize PTE and receiver coil size. The experimental results show that PTE in the tangential boundary plane Misalignment increases by 5-10% when compared to coil array circles and increases by 82% when compared to single coil circles. 
Volume: 22
Issue: 2
Page: 638-647
Publish at: 2021-05-01

Dynamic composition components based on machine learning: architecture design and process

10.11591/ijeecs.v22.i2.pp1135-1143
Younes Zouani , Abdelmounaim Abdali , Charafeddine Ait Zaouiat
The dynamic composition of components is an emerging concept that aims to allow a new application to be constructed based on a user’s request. Three main ingredients must be used to achieve the dynamic composition of components: goal, scenario, and context-awareness. These three ingredients must be completed by artificial intelligence (AI) techniques that help process discovery and storage. This paper presents framework architecture for the dynamic composition of components that can extract expressed goals, deduce implicit ones using AI. The goal will be combined with pertinent contextual data, to compose the relevant components that meet the real requirements of the user. The core element of our proposed architecture is the composer component that (i) negotiate user goal, (ii) load the associated scenarios and choose the most suitable one based on user goal and profile, (iii) get binding information of scenario’s actions, (iv) compose the loaded actions, and (v) store the new component as a tree of actions enabled by contextual or process constraint. In our e-learning proven of concept, we consider five components: composer component, reader component, formatter component, matcher component, and executor component. These five components stipulate that a course is the combination of existing/scrapped chapters that have been adapted to a user profile in terms of language, level of difficulty, and prerequisite. The founding result shows that AI is not only an element that enhances system performance in terms of timing response but a crucial ingredient that guides the dynamic composition of components. 
Volume: 22
Issue: 2
Page: 1135-1143
Publish at: 2021-05-01
1 2 3
...
2097 2098
Show 1078 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