Articles
9,199 Documents
Hierarchy based firefly optimized K-means clustering for complex question answering
A. Chandra Obula Reddy;
K. Madhavi
Indonesian Journal of Electrical Engineering and Computer Science Vol 17, No 1: January 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v17.i1.pp264-272
Complex Question Answering (CQA) is commonly used for answering community questions which requires human knowledge for answering them. It is essential to find complex question answering system for avoiding the complexities behind the question answering system. In the present work, we proposed Hierarchy based Firefly Optimized k-means Clustering (HFO-KC) method for complex question answering. Initially, the given input query is preprocessed. It eliminates the way of misclassification when comparing the strings. In order to enhance the answer selection process, the obtained keywords are mapped into the candidate solution. After mapping, the obtained keywords are segmented. Each segmentation forms a new query for answer selection and various number of answers selected for each query. Okapi-25 similarity computation is utilized for the process of document retrieval. Then the answers selected are classified with K means clustering which forms the hierarchy for each answer. Finally the firefly optimization algorithm is used for selecting the best quality of answer from the hierarchy.
Super-resolution Imaging Realization of Costas Signal
Wang Liang;
Shang Chao-xuan;
He Qiang;
Han Zhuang-zhi;
Wang Yong-lei
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 2: February 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Although the ambiguity function of Costas-coded FH (Frequency Hopping) signal has a thumbtack nature, its resolution in range and velocity domain is constraint by the bandwidth and time duration also. If one target is much stronger than the others in multi-targets detection environment, the sidelobes pedestal will make possible masking via the traditional stretch signal processing. Based on the diffraction model of radar target, sparse decomposition and compressed sensing are applied to reconstruct the radar range-velocity profiles with super-resolution. In order to get the super-resolution profiles, a sparse dictionary is constructed based on the Costas echo model, different sparsity measure functions are studied, and the penalizing function method and the Lagrangian multipliers method are introduced to get the optimal result. Some schemes are introduced to get the optimal atom and the differences between these schemes are compared via simulations. DOI : http://dx.doi.org/10.11591/telkomnika.v12i2.3904
Real Time Break Point Detection Technique (RBPD) in Computer Mouse Trajectory
Seyed Yashar Banihashem;
Nor Azan Mat Zin;
Noor Faezah Mohd Yatim;
Norlinah Mohamed Ibrahim
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 5: May 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
This paper presents a new technique for detecting break points in computer mouse trajectories called Real time Break Point Detection (RBPD). The mouse trajectory from motor-disabled people contains a lot of break points. RBPD can detect these break points by adapting to the user’s tremor level. To test the effectiveness of this new technique, an experimental study involving five participants suffering from Parkinson’s disease (PD) was conducted. The test results showed that RBPD technique is effectiveness in detecting break points. DOI: http://dx.doi.org/10.11591/telkomnika.v11i5.2507
Decision Support Dashboard in OpenERP
Laila Eken;
Belaid Bouikhalene;
Mohamed Fakir
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 12: December 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v12.i12.pp8326-8334
This work focuses on the analysis and design of decision support dashboard in OpenERP. With the aim to improve the Operational Information System OIS of the Moroccan university, Hassan 1st University of SETTAT launched MISSION project, in association with 22 academic and institutional partners of Morocco and the European Union. This project is to improve the management of Moroccan universities. The vision of the MISSION project is to modernize the governance of universities in order to improve the quality of services offered by the university administration. The basic idea is to provide each partner university in a OIS using open source ERP (OpenERP) and integrating 4 bricks trades (schooling, Finance, Human Resource Management (HRM) and Heritage). This operational information system is not completed if and only if there is a Strategic Information System (SIS) that uses the information provided by the first to give university leaders the opportunity to take long-term decisions and this is the aim of the second. One of the tools of SIS we find dashboards.
Deep learning in non coding variant (a brief overview)
Lee Kuan Xin;
Afnizanfaizal Abdullah
Indonesian Journal of Electrical Engineering and Computer Science Vol 18, No 3: June 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v18.i3.pp1432-1438
The 21st centuries were deemed to be the era of big data. Data driven research had become a necessity. This hold true not only in the business world, yet also in the field of biomedical world. From a few years of biological data extraction and derivation. With the advancement of Next Generation Sequencing, genomics data had grown to become an ambiguous giant which could not keep up with the pace of its advancement in it analysis counter parts. This results in a large amount of unanalysed genomic data. These genomic data consist not only plain information, researcher had discovered the potential of most gene called the non-coding variant and still failing in identifying their function. With the growth in volume of data, there is also a growth of hardware or technologies. With current technologies, we were able to implement a more complex and sophisticated algorithm in analysis these genomics data. The domain of deep learning had become a major interest of researcher as it was proven to have achieve a significant success in deriving insight from various field. This paper aims to review the current trend of non-coding variant analysis using deep learning approach.
Video Fire Detection Algorithm using Multi-Feature Fusion
Mengxin LI;
Weijing XU;
Ke XU;
Jingjing FAN;
Dingding HOU
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 10: October 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
At present, the moving target detection and flame characteristics extraction almost become the most important parts in majority of video fire detection systems. Through the above two-part study, a new fire features detection method is presented in precise moving target area. That is, using the improved background difference method and flame features (such as the color and uniformity, Wavelet energy, stroboscopic and contour features) to detect fire. Experiments show that this method can improve theaccuracy and anti-interference ability of fire detection. DOI: http://dx.doi.org/10.11591/telkomnika.v11i10.3340
X-Band 5-bit MMIC Digital Attenuator With Low Phase Shift
Chengpeng Liu;
Xin Xu;
Zhengrong He
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 6: June 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
This paper presents the x-band 5-bit MMIC digital attenuator with low phase shift. Phase compensation techniques were used in the MMIC design to reduce the phase shift. This attenuator is fabricated with 0.2µm GaAs PHEMT process. Measurement results of the developed MMIC chips in the x-band show that the 5-bit MMIC digital attenuator has 0.5dB resolution and 15.5dB dynamic attenuation range, input return losses was less than 10dB and output return losses was less than 13dB for all attenuation states, RMS is less than 0.2dB; insertion loss is less than 3.8dB; phase shift error is less than 5°for 35 attenuation states; The MMIC chip size is 1.58 mm×2.95 mm×0.1mm. DOI : http://dx.doi.org/10.11591/telkomnika.v12i6.4742
Effects of soil profile on the transient performance of substation grounding system
Zulkurnain Adul Malek;
Mohammad Shahrin Affendy Yaman;
Muhammad Adnan
Indonesian Journal of Electrical Engineering and Computer Science Vol 20, No 2: November 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v20.i2.pp870-877
Lightning transient characteristic of the grounding grid is fundamental for optimum performance of lightning protection of a substation. In order to design an appropriate grounding system for such substation, it is important to study its transient characteristics because the high impulse current is significantly different compared to power frequency current. In this paper, substation grounding grid model was developed using CDEGS software to analyze the grid transient performance in terms of ground potential rise (GPR), touch voltage and step voltage when the grounding system is struck by a lightning impulse current. Several parameters, such as lightning current amplitude, feed point and the number of sub-grids, were altered to study their relationship with the transient performance. The maximum transient GPR, touch voltage, and step voltage increase as the lightning current amplitude increase. The maximum transient GPR and step voltage are the highest at the corner of the grounding grid while the maximum touch voltage is the highest at the centre of the grounding grid. In addition, the maximum transient GPR and step voltage decrease when the number of sub-grid increases. In contrast, the touch voltage slightly increases as the number of sub-grid increases. The maximum transient GPR, and step voltage are the highest at the 2-layer and the lowest at the uniform soil or single-layer soil.
Brute force algorithm implementation for traveljoy travelling recommendation system
K.A.F.A. Samah;
N. Sabri;
R. Hamzah;
R. Roslan;
N.A. Mangshor;
A.A.M. Asri
Indonesian Journal of Electrical Engineering and Computer Science Vol 16, No 2: November 2019
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v16.i2.pp1042-1049
This paper presents the Brute Force algorithm implementation for TravelJoy Travelling Recommendation System. Due to overwhelmed information in the internet, travelers faced difficulties in finding and comparing which places in Melaka that worth to visit. Melaka is a well-known place as one of the most popular tourist spots in Malaysia, famous with historical places. All the mentioned problems were time-consuming and required lots of efforts for manual comparison between places and planning the trip itinerary. An efficient application system is needed to assist travelers in planning their trip itinerary by providing details of interesting place in Melaka, budget estimating and recommendation of sequence places which to visit. The TravelJoy application applied Traveling Salesman Problem (TSP) concept using Brute Force algorithm in determining the least time duration for the selected places and adapting Expected Time Arrival (ETA). It was found through Brute Force algorithm adaptation; the recommendation system is reliable based on the functional and reliability testing with t-test result of 0.00067, indicates the system is accepted.
Mixed Programming Realization of the EMD-WVD Combined Method
Miaozhong Sun;
Hongtao Tang;
Yuanli Xu
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 4: April 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Winger-Ville Distribution (WVD) possesses high time-frequency concentration and resolutions, but brings serious cross-terms in process of a multi-component signal to distort greatly the result of time-frequency analysis. Because of this the use of the WVD is limited for many applications. In this paper a combined method is proposed: Empirical Mode Decomposition (EMD) is first used to decompose the original signal into a series of Intrinsic Mode Functions (IMFs), then false IMFs among them are eliminated according to the correlation coefficients between each IMF and the original signal, WVD is utilized to analyze the remanent IMFs, finally each WVD is added linearly with together to reconstruct the whole WVDs of the original signal. In order to carry out and validate the combined method, a time-frequency analytic system is designed and realized by using MATLAB and Delphi mixed programming based on COM (Component Object Model) module technology. This system is used to perform vibration signal time-frequency analysis of a grinding machine. The analytic results show validity of the combinedl method and success of the mixed programming. DOI: http://dx.doi.org/10.11591/telkomnika.v11i4.2360