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

29,905 Article Results

Angular Symmetric Axis Constellation Model for Off-line Odia Handwritten Characters Recognition

10.11591/ijict.v7i2.pp96-104
Pyari Mohan Jena , Soumya Ranjan Nayak
Optical character recognition is one of the emerging research topics in the field of image processing, and it has extensive area of application in pattern recognition. Odia handwritten script is the most research concern area because it has eldest and most likable language in the state of odisha, India. Odia character is a usually handwritten, which was generally occupied by scanner into machine readable form. In this regard several recognition technique have been evolved for variance kind of languages but writing pattern of odia character is just like as curve appearance; Hence it is more difficult for recognition. In this article we have presented the novel approach for Odia character recognition based on the different angle based symmetric axis feature extraction technique which gives high accuracy of recognition pattern. This empirical model generates a unique angle based boundary points on every skeletonised character images. These points are interconnected with each other in order to extract row and column symmetry axis. We extracted feature matrix having mean distance of row, mean angle of row, mean distance of column and mean angle of column from centre of the image to midpoint of the symmetric axis respectively. The system uses a 10 fold validation to the random forest (RF) classifier and SVM for feature matrix. We have considered the standard database on 200 images having each of 47 Odia character and 10 Odia numeric for simulation. As we have noted outcome of simulation of SVM and RF yields 96.3% and 98.2% accuracy rate on NIT Rourkela Odia character database and 88.9% and 93.6% from ISI Kolkata Odia numerical database.
Volume: 7
Issue: 2
Page: 96-104
Publish at: 2018-08-01

Bi-directional Beams Waveguide Slotted Antenna at Millimeter Wave

10.12928/telkomnika.v16i4.9057
Muataz W.; University Technology Malaysia Sabri , Noor A.; University Technology Malaysia Murad , Mohammed K.A.; University Technology Malaysia Rahim
This paper focused on designing a bi-directional beams waveguide slotted antenna at millimetre wave spectrum. Waveguide slotted antenna is known for its highly directional pattern. By having bi-directional pattern, the capacity of system coverage can be expanded. The design is implemented by using antenna slot theory on a waveguide structure. The slotted are made on two wall surfaces and the performance is compared to the slotted on single wall. The two models designs are simulated using Computer Simulation Technology (CST) microwave software. The simulation results show that both models operate at 30 GHz with minimum reflection coefficient of -24.63 and -25.01 dB respectively. The two models achieved a fair high gain at 15.5 dB and 13.3 dB with directional beamwidth of 8.9 degree. The proposed bi-directional beams structure achieved a comparable gain in both directions when compared to the single direction.
Volume: 16
Issue: 4
Page: 1515-1521
Publish at: 2018-08-01

Applied Healthcare Knowledge Management for Hospital in Clinical Aspect

10.12928/telkomnika.v16i4.5673
Sevenpri; Bina Nusantara University Candra , Ichsan Kurniawan; Bina Nusantara University Putrama
Medical industry uses the information as a critical factor in running the three aspects of hospital management which includes administrative, financial and clinical. Objectives to be achieved is to identify healthcare knowledge resources and models of knowledge sharing, identifying culture, strategy and knowledge management supporting facilities, plotting knowledge resources and mapping supporting features of knowledge portals as well as doing analysis and design of healthcare knowledge management portal that developed.In achieving the purpose of analysis and design of healthcare knowledge management portal, is done through several stages of the methodology, where the identification process carried out primary and secondary data collection, while the analysis on the management aspects was performed cultural analysis with OCAI methods and the analysis and design of information systems with OOAD approach using UML models. PELNI Hospital is using for this case study. From analysis and design of healthcare knowledge management portal is expected to get a picture of the current organizational culture and the expected culture, the description of network infrastructure and organizational strategies related to resource and knowledge destination to produce a Knowledge Management Portal.
Volume: 16
Issue: 4
Page: 1760-1770
Publish at: 2018-08-01

WCLOUDVIZ: Word Cloud Visualization of Indonesian News Articles Classification Based on Latent Dirichlet Allocation

10.12928/telkomnika.v16i4.8194
Retno; Universitas Diponegoro Kusumaningrum , Satriyo; Universitas Diponegoro Adhy , Suryono; Universitas Diponegoro Suryono
Latent Dirichlet Allocation (LDA) is a widely implemented approach for extracting hidden topics in documents generated by soft clustering of a word based on document co-occurrence as a multinomial probability distribution over terms. Therefore, several visualizations have been developed, such as matrices design, text-based design, tree design, parallel coordinates, and force-directed graphs. Furthermore, based on a set of documents representing a class (category), we can implement classification task by comparing topic proportion for each class and topic proportion for the testing document by using Kullback-Leibler Divergence (KLD). Therefore, the purpose of this study is to develop a system for visualizing the output of LDA as a classification task. The visualization system consists of two parts: bar chart and dependent word cloud. The first visualization aims to show the trend of each category, while the second visualization aims to show the words that represent each selected category in a word cloud. This visualization is subsequently called WCloudViz. It provides clear, understandable and preferably shared the result.
Volume: 16
Issue: 4
Page: 1752-1759
Publish at: 2018-08-01

Assessment Analytic Theoretical Framework Based on Learners’ Continuous Learning Improvement

10.11591/ijeecs.v11.i2.pp682-687
M. Hamiz , M. Bakri , Norhaslinda Kamaruddin , Azlinah Mohamed
Currently, university students are required to follow stringent curriculum structure regardless of their performance. Personalized learning is not being offered resulting the whole cohort must compy to a customized fixed curriculum design. This is because the designed curriculum does not take into account different students’ attainment. Furthermore, there is a mismatched between supply and demand of graduates’ skill sets to fulfil the requirement of industry. Due to these issues, employers face difficulties in finding suitable high-skilled worker which contributes to large number of unemployed graduates. Thus, a systematic intervention of students’ learning process is essential to construct informed and strategic responses in order to manage challenges and minimize skill mismatch, at the same time providing adequate fundamental knowledge. In this paper, an assessment analytics framework is proposed based on automated extracted skill sets from curriculum documents and individual performance to recommend adaptive learners’ learning system (ALLS). By preparing the graduates with the required industry skill sets, the graduates’ unemployment rate is envisaged to reduce.
Volume: 11
Issue: 2
Page: 682-687
Publish at: 2018-08-01

Metamodel-based Optimization of a PID Controller Parameters for a Coupled-tank System

10.12928/telkomnika.v16i4.9069
Marwan; Universiti Teknologi Malaysia Nafea , Abdul Rasyid Mohammad; Universiti Teknologi Malaysia Ali , Jeevananthan; Jabil Circuit Guangzhou Economic and Technological Development District Baliah , Mohamed Sultan; Universiti Teknologi Malaysia Mohamed Ali
Liquid flow and level control are essential requirements in various industries, such as paper manufacturing, petrochemical industries, waste management, and others. Controlling the liquids flow and levels in such industries is challenging due to the existence of nonlinearity and modeling uncertainties of the plants. This paper presents a method to control the liquid level in a second tank of a coupled-tank plant through variable manipulation of a water pump in the first tank. The optimum controller parameters of this plant are calculated using radial basis function neural network metamodel. A time-varying nonlinear dynamic model is developed and the corresponding linearized perturbation models are derived from the nonlinear model. The performance of the developed optimized controller using metamodeling is compared with the original large space design. In addition, linearized perturbation models are derived from the nonlinear dynamic model with time-varying parameters.
Volume: 16
Issue: 4
Page: 1590-1596
Publish at: 2018-08-01

An Early Drowning Detection System for Internet of Things (IoT) Applications

10.12928/telkomnika.v16i4.9046
Muhammad Ramdhan; Universiti Teknologi Malaysia MS , Muhammad; Universiti Teknologi Malaysia Ali , Paulson Eberechukwu; Universiti Teknologi Malaysia N , Nurzal Effiyana; Universiti Teknologi Malaysia G , Samura; Universiti Teknologi Malaysia Ali , Kamaludin; Universiti Teknologi Malaysia M.Y
Drowning is the leading cause of injury or death for children and teenagers. Designing a drowning detection device by implementing an Internet of Thing (IoT) is needed. An Early Drowning Detection System (EDDS) is a system that gives an early alarm to the guardians (parents and lifeguard) if the detector triggered an abnormal heartbeat and the victims are submerged under the water for a long time. A microcontroller was used to control the signal received from a pulse sensor and time for the signal lost under the water before it is transmitted to the access point. The access point acts as a data forwarding to the database via an internet connection. Universal Asynchronous Receiver/Transmitter (UART) 433MHz radio frequency transceiver has been used to create the wireless communication between drowning detection device and monitoring hub. A triggered warning signal will be transmitted to the guardians via Android apps and web page.
Volume: 16
Issue: 4
Page: 1870-1876
Publish at: 2018-08-01

Biometric Analysis of Leaf Venation Density Based on Digital Image

10.12928/telkomnika.v16i4.7322
Agus; Universitas Teknokrat Indonesia Ambarwari , Yeni; Bogor Agricultural University Herdiyeni , Irman; Bogor Agricultural University Hermadi
The density level in the leaf venation type has different characteristics. These different characteristics explain the environment in which plants grow, such as habitat, vegetation, physiology and climate. This research aims to measure of leaf venation density, leaf venation feature analysis and then identifying plants based on venation type. Stages of this research include leaf image data collection, segmentation, vein detection, feature extraction, feature selection, classification, evaluation and ending with analysis. The results of this study indicate that the level of leaf venation density is quite good is the type of venation paralellodromous, acrodromous and pinnate. Based on the selection of features using Boruta Algorithm, obtained 19 most important features that represent the type of leaf venation. This is reinforced by the average of accuracy produced at the time of classification using SVM, which amounted to 77.57%.
Volume: 16
Issue: 4
Page: 1735-1744
Publish at: 2018-08-01

Multi-class K-support Vector Nearest Neighbor for Mango Leaf Classification

10.12928/telkomnika.v16i4.8482
Eko; University of Bhayangkara Surabaya Prasetyo , R. Dimas; University of Bhayangkara Surabaya Adityo , Nanik; Institut Teknologi Sepuluh Nopember Suciati , Chastine; Institut Teknologi Sepuluh Nopember Fatichah
K-Support Vector Nearest Neighbor (K-SVNN) is one of methods for training data reduction that works only for binary class. This method uses Left Value (LV) and Right Value (RV) to calculate Significant Degree (SD) property. This research aims to modify the K-SVNN for multi-class training data reduction problem by using entropy for calculating SD property. Entropy can measure the impurity of data class distribution, so the selection of the SD can be conducted based on the high entropy. In order to measure performance of the modified K-SVNN in mango leaf classification, experiment is conducted by using multi-class Support Vector Machine (SVM) method on training data with and without reduction. The experiment is performed on 300 mango leaf images, each image represented by 260 features consisting of 256 Weighted Rotation- and Scale-invariant Local Binary Pattern features with average weights (WRSI-LBP-avg) texture features, 2 color features, and 2 shape features. The experiment results show that the highest accuracy for data with and without reduction are 71.33% and 71.00% respectively. It is concluded that K-SVNN can be used to reduce data in multi-class classification problem while preserve the accuracy. In addition, performance of the modified K-SVNN is also compared with two other methods of multi-class data reduction, i.e. Condensed Nearest Neighbor Rule (CNN) and Template Reduction KNN (TRKNN). The performance comparison shows that the modified K-SVNN achieves better accuracy.
Volume: 16
Issue: 4
Page: 1826-1837
Publish at: 2018-08-01

News Reliability Evaluation using Latent Semantic Analysis

10.12928/telkomnika.v16i4.9062
Guo; Multimedia University Xiaoning , Tan De; Multimedia University Zhern , Soo Wooi; Multimedia University King , Tan Yi; Multimedia University Fei , Lam Hai; Multimedia University Shuan
The rapid rise and widespread of ‘Fake News’ has severe implications in the society today. Much efforts have been directed towards the development of methods to verify news reliability on the Internet in recent years. In this paper, an automated news reliability evaluation system was proposed. The system utilizes term several Natural Language Processing (NLP) techniques such as Term Frequency-Inverse Document Frequency (TF-IDF), Phrase Detection and Cosine Similarity in tandem with Latent Semantic Analysis (LSA). A collection of 9203 labelled articles from both reliable and unreliable sources were collected. This dataset was then applied random test-train split to create the training dataset and testing dataset. The final results obtained shows 81.87% for precision and 86.95% for recall with the accuracy being 73.33%.
Volume: 16
Issue: 4
Page: 1704-1711
Publish at: 2018-08-01

Fuzzy Logic Enhanced Direct Torque Control with Space Vector Modulation

10.11591/ijeecs.v11.i2.pp704-710
Siaw-Paw Koh , Sieh-Kiong Tiong , Kharudin Ali , Ahmed Abdalla
Over the past few years, multiple types of modifications have been proposed onto the Direct Torque Control (DTC) scheme. Among others is the implementation of Space Vector Modulation (SVM). In this paper, two new control strategies are proposed onto an SVM-DTC. Instead of using PI torque and flux controllers, a fuzzy logic control method is implemented in the proposed modification to achieve a more constant switching frequency while minimizing the torque error. The fuzzy logic controller controls the voltages in direct and quadratic reference frame (Vd, Vq). This approach fully utilizes the switching capability of the inverter and thus improving the overall system performance. To overcome issues in open loop stator flux such as DC drift and saturation, a closed loop estimation method of stator flux is also proposed based on voltage model and low pass filter. The performance of the proposed control strategy is benchmarked with that of a conventional DTC–SVM. Simulations and experiments were carried out and the results show that the proposed method outperforms the conventional DTC-SVM in terms of DC-offset elimination and overall system robustness. Over the past few years, multiple types of modifications have been proposed onto the Direct Torque Control (DTC) scheme. Among others is the implementation of Space Vector Modulation (SVM). In this paper, two new control strategies are proposed onto an SVM-DTC. Instead of using PI torque and flux controllers, a fuzzy logic control method is implemented in the proposed modification to achieve a more constant switching frequency while minimizing the torque error. The fuzzy logic controller controls the voltages in direct and quadratic reference frame (Vd, Vq). This approach fully utilizes the switching capability of the inverter and thus improving the overall system performance. To overcome issues in open loop stator flux such as DC drift and saturation, a closed loop estimation method of stator flux is also proposed based on voltage model and low pass filter. The performance of the proposed control strategy is benchmarked with that of a conventional DTC–SVM. Simulations and experiments were carried out and the results show that the proposed method outperforms the conventional DTC-SVM in terms of DC-offset elimination and overall system robustness. 
Volume: 11
Issue: 2
Page: 704-710
Publish at: 2018-08-01

Mixed Integer Linear Programming for Maintenance Scheduling in Power System Planning

10.11591/ijeecs.v11.i2.pp607-613
S.M. Hussin , M.Y. Hassan , L. Wu , M.P. Abdullah , N. Rosmin , M.A. Ahmad
This paper discussed the merit of mixed-integer linear programming (MILP)-based approach against Lagrangian relaxation (LR)-based approach in solving generation and transmission maintenance scheduling problem. MILP provides a straightforward solution by formulating coupling constraints equations so that these sub-problems can be solved simultaneously without involving multipliers. In LR-based approach, generation and transmission maintenance scheduling, and security-constrained unit commitment have been solved individually and the integration was realized through a series of multipliers which has caused computational burden to the system. Numerical case studies were evaluated on the 6-bus system. A comparative study is carried out between the MILP and LR approaches. Simulation results indicate that the maintenance schedule derived by the proposed MILP approach outperforms the LR in terms of operational cost savings and gap tolerance. The operating cost could be saved up to 5% and the gap tolerance achieved is 0.01% as compared to 0.14% by LR.
Volume: 11
Issue: 2
Page: 607-613
Publish at: 2018-08-01

Token-based Single Sign-on with JWT as Information System Dashboard for Government

10.12928/telkomnika.v16i4.8388
I Putu Arie; Udayana University Pratama , Linawati; Udayana University Linawati , Nyoman Putra; Udayana University Sastra
Various web-based information systems are developed by Indonesian government to improve quality of services for their society. It encourages users, generally civil servants, to perform different authentications on used information systems and have to remember credentials. Account management of the users poses another challenge for administrators. Single Sign-On (SSO) can be the solution by providing a service of centralized authentication and user account management. This study applies a token-based SSO architecture and uses Json Web Token (JWT) to grant permission authorities, since JWT can provide a claim process between 2 parties. Additionally, the built-in dashboard lists associated information systems to facilitate accessing for the authenticated users. This study will discuss JWT implementation on the dashboard of government information systems that implements SSO, which will generate the permission authorities securely for connected information systems on SSO.
Volume: 16
Issue: 4
Page: 1745-1751
Publish at: 2018-08-01

Evaluation of Research Standards at Ministry of Research, Technology and Higher Education with I-MR Map Control Analysis

10.12928/telkomnika.v16i4.10491
Muhammad; University of Indonesia Dimyati , Akhmad; Islamic University of Indonesia Fauzy
In order to accommodate research activities at all universities in Indonesia, the Directorate Genereal of Strengthening for Research and Development, Ministry of Research, Technology, and Higher Education (Kemenristekdikti) of the Republic of Indonesia established research quality standard. The standard includes the minimum targets that must be achieved by each University at the period of conducting the research activity. However, until now there has been no measurement to find out whether the existing standard was good enough or needs to be evaluated. Therefore, this study was conducted to measure the standards. The method used was the analysis of I-MR (Individual and Moving Range) control chart to see the performance of the standard. The results show that existing research schemes have encouraged the improvement of international publications, but have not yet maximized the production of other outputs such as textbooks, accredited national publications, intellectual property rights, and ptototypes. The result of the research was expected to be used as material for evaluation and improvement of policy to improve the quality of research standard in Kemenristekdikti.
Volume: 16
Issue: 4
Page: 1449-1456
Publish at: 2018-08-01

Designing Fuzzy Expert System to Identify Child Intelligence

10.12928/telkomnika.v16i4.7779
Muhamad Bahrul; Esa Unggul University Ulum , Vitri; YARSI University Tundjungsari
Every child is special and has her/his own unique potential. Identifying child’s potential in early age is important for teaching purpose since every child has difference intelligence and interest. Therefore children’s teaching and learning process should be delivered based on child’s interest and intelligence, instead of forcing children to excel in every subject. We propose our research to identify child’s intelligence by designing fuzzy expert system. The system works based on several input data of children’s multiple intelligences. The fuzzy expert system is developed using 25 input variables and resulted in 9 output variables. The system classifies the result based on 9 types of intelligence in human, where each exhibits different level. We produce 81 rules with fuzzy set of three different levels value (high, moderate, or low) for every kind of intelligence. The result of this research is very useful to help parents and teachers for determining their method of teaching based on children’s potential.
Volume: 16
Issue: 4
Page: 1688-1696
Publish at: 2018-08-01
1 2 3
...
1993 1994
Show 1425 of 1994

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