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

29,922 Article Results

Deep learning model for thorax diseases detection

10.12928/telkomnika.v18i1.12997
Ghada A.; Mustansiriyah University Shadeed , Mohammed; Mustansiriyah University A. Tawfeeq , Sawsan; Mustansiriyah University M. Mahmoud
Despite the availability of radiology devices in some health care centers, thorax diseases are considered as one of the most common health problems, especially in rural areas. By exploiting the power of the Internet of things and specific platforms to analyze a large volume of medical data, the health of a patient could be improved earlier. In this paper, the proposed model  is based on pre-trained ResNet-50  for diagnosing thorax diseases. Chest x-ray images are cropped to extract the rib cage part from the chest radiographs. ResNet-50 was re-train on Chest x-ray14 dataset where a chest radiograph images are inserted into the model to determine if the person is healthy or not. In the case of an unhealthy patient, the model can classify the disease into one of the fourteen chest diseases. The results show the ability of ResNet-50 in achieving impressive performance in classifying thorax diseases.
Volume: 18
Issue: 1
Page: 441-449
Publish at: 2020-02-01

Review on controller design in pneumatic actuator drive system

10.12928/telkomnika.v18i1.12626
Syamiza; Universiti Teknikal Malaysia Melaka Jamian , S. N. S.; Universiti Teknikal Malaysia Melaka. Salim , M. N.; Universisti Teknikal Malaysia Melaka Kamarudin , M.; Universiti Teknikal Malaysia Melaka. Zainon , M. S.; Universiti Teknikal Malaysia Melaka. Syed Mohamed , L.; Universiti Teknikal Malaysia Melaka Abdullah , M. A. M.; Universiti Teknikal Malaysia Melaka. Hanafiah
A pneumatic actuator is a device that converts compressed air into mechanical energy to perform varieties of work. It exhibits high nonlinearities due to high friction forces, compressibility of air and dead band of the spool movement which is difficult to manage and requires an appropriate controller for better performance. The purpose of this study is to review the controller design of pneumatic actuator recommended by previous researchers from the past years. Initially, the basic views of the pneumatic will be presented in terms of introduction to the pneumatic actuator and its applications in industries. At the end of this review, discussions on the design of the controllers will be concluded and further research will be proposed along with the improvement of control strategies in the pneumatic actuator systems.
Volume: 18
Issue: 1
Page: 332-342
Publish at: 2020-02-01

i-Eclat: performance enhancement of eclat via incremental approach in frequent itemset mining

10.12928/telkomnika.v18i1.13497
Wan Aezwani; Universiti Sultan Zainal Abidin Wan Abu Bakar , Mustafa; Universiti Malaysia Terengganu Man , Mahadi; Universiti Malaysia Terengganu Man , Zailani; Universiti Malaysia Kelantan Abdullah
One example of the state-of-the-art vertical rule mining technique is called equivalence class transformation (Eclat) algorithm. Neither horizontal nor vertical data format, both are still suffering from the huge memory consumption. In response to the promising results of mining in a higher volume of data from a vertical format, and taking consideration of dynamic transaction of data in a database, the research proposes a performance enhancement of Eclat algorithm that relies on incremental approach called an Incremental-Eclat (i-Eclat) algorithm. Motivated from the fast intersection in Eclat, this algorithm of performance enhancement adopts via my structured query language (MySQL) database management system (DBMS) as its platform. It serves as the association rule mining database engine in testing benchmark frequent itemset mining (FIMI) datasets from online repository. The MySQL DBMS is chosen in order to reduce the preprocessing stages of datasets. The experimental results indicate that the proposed algorithm outperforms the traditional Eclat with 17% both in chess and T10I4D100K, 69% in mushroom, 5% and 8% in pumsb_star and retail datasets. Thus, among five (5) dense and sparse datasets, the average performance of i-Eclat is concluded to be 23% better than Eclat.
Volume: 18
Issue: 1
Page: 562-570
Publish at: 2020-02-01

Negative resistance amplifier circuit using GaAsFET modelled single MESFET

10.12928/telkomnika.v18i1.10120
Olasunkanmi; Covenant University Ojewande , Charles; Covenant University Ndujiuba , Adebiyi A.; Covenant University Adelakun , Segun I.; Covenant University Popoola , Aderemi A.; Covenant University Atayero
Negative resistance devices have attracted much attention in the wireless communication industry because of their low cost, better performance, high speed, and reduced power requirements. Although negative resistance circuits are non-linear circuits, they are associated with distortion, which may either be amplitude-to-amplitude distortion or amplitude-to-phase distortion. In this paper, a unique way of realizing a negative resistance amplifier is proposed using a single metal-semiconductor field-effect transistor (MESFET). Intermodulation distortion test (IMD) is performed to evaluate the characteristic response of the negative resistance circuit amplifier to different bias voltages using the harmonic balance (HB) of the advanced designed software (ADS 2016). The results obtained are compared to those of a conventional distributed amplifier. The findings of this study showed that the negative resistance amplifier spreads over a wider frequency output with reduced power requirements while the conventional distributed amplifier has a direct current (DC) offset with output voltage of 32.34 dBm.
Volume: 18
Issue: 1
Page: 179-190
Publish at: 2020-02-01

The performance of COR optimisation using different constraint handling strategies to solve ELD

10.11591/ijeecs.v17.i2.pp680-688
Azralmukmin Azmi , Samila Mat Zali , Mohd Noor Abdullah , Mohammad Faridun Naim Tajuddin , Siti Rafidah Abdul Rahim
This research compares the performance of Competitive Over Resources (COR) optimisation method using a different type of constraint handling strategy to solve the economic load dispatch (ELD) problem. Previously, most research focused on proposing various optimisation techniques using the Penalty Factor Strategy (PFS) to search for a better global optimum. The issue using the penalty factor is that it is difficult to find the correct tune of constant value that influences the algorithm to find the solution. The other technique is using Feasible Solution Strategy (FSS), the idea of which is to locate the infeasible particle to the feasible solution and avoid being trapped by the unsuccessful condition of constraint. This paper investigates the performance of PFS and FSS on the COR optimisation method for solving ELD. Both strategies have been tested on two standard test systems to compare the performance in terms of a global solution, robustness and convergence. The simulation shows that FSS is a better solution compared to PFS.
Volume: 17
Issue: 2
Page: 680-688
Publish at: 2020-02-01

Halftoning-based BTC image reconstruction using patch processing with border constraint

10.12928/telkomnika.v18i1.12837
Heri; Universitas Sebelas Maret (UNS) Prasetyo , Chih-Hsien; National Ilan University Hsia , Berton Arie Putra; Universitas Sebelas Maret (UNS) Akardihas
This paper presents a new halftoning-based block truncation coding (HBTC) image reconstruction using sparse representation framework. The HBTC is a simple yet powerful image compression technique, which can effectively remove the typical blocking effect and false contour. Two types of HBTC methods are discussed in this paper, i.e., ordered dither block truncation coding (ODBTC) and error diffusion block truncation coding (EDBTC). The proposed sparsity-based method suppresses the impulsive noise on ODBTC and EDBTC decoded image with a coupled dictionary containing the HBTC image component and the clean image component dictionaries. Herein, a sparse coefficient is estimated from the HBTC decoded image by means of the HBTC image dictionary. The reconstructed image is subsequently built and aligned from the clean, i.e. non-compressed image dictionary and predicted sparse coefficient. To further reduce the blocking effect, the image patch is firstly identified as “border” and “non-border” type before applying the sparse representation framework. Adding the Laplacian prior knowledge on HBTC decoded image, it yields better reconstructed image quality. The experimental results demonstrate the effectiveness of the proposed HBTC image reconstruction. The proposed method also outperforms the former schemes in terms of reconstructed image quality.
Volume: 18
Issue: 1
Page: 394-406
Publish at: 2020-02-01

Design and development of smart emergency light

10.12928/telkomnika.v18i1.13934
S.; TKR College of Engineering and Technology Narasimha , Surender Reddy; Woosong University Salkuti
The demand for electricity is increasing day-by-day and frequent power cuts is causing many problems in various areas such as household, domestic, farms, etc. Due to limited amount of power generation at power station and due to shortage of non-renewable sources, uninterruptible power supply being a biggest challenge in the entire world. In this paper, a smart emergency light is designed, developed and tested for use it in various applications such as home, industries, agricultural sector and shops, etc. The developed energy lamp has no running cost and has low initial cost. The main objective of this work is to provide the smart emergency light with solar power to the farmers. This work will help the farmers in many ways such as protecting the fields from yield animals. It can also be used as emergency light and entertainment, etc. The main applications of this work is that it can used as FM radio, USB charging, music by memory card, mini fan, torch light, etc. This can also be controlled by remote. The battery can be used for all these applications. This battery can be charged by two ways using solar energy and AC mains supply. The developed lamp is tested in the real time environment.
Volume: 18
Issue: 1
Page: 358-364
Publish at: 2020-02-01

Ensemble deep learning for tuberculosis detection

10.11591/ijeecs.v17.i2.pp1014-1020
Mohd Hanafi Ahmad Hijazi , Leong Qi Yang , Rayner Alfred , Hairulnizam Mahdin , Razali Yaakob
Tuberculosis (TB) is one of the deadliest infectious disease in the world. TB is caused by a type of tubercle bacillus called Mycobacterium Tuberculosis. Early detection of TB is pivotal to decrease the morbidity and mortality. TB is diagnosed by using the chest x-ray and a sputum test. Challenges for radiologists are to avoid confused and misdiagnose TB and lung cancer because they mimic each other. Semi-automated TB detection using machine learning found in the literature requires identification of objects of interest. The similarity of tissues, veins and small nodules presenting the image at the initial stage may hamper the detection. In this paper, an approach to detect TB, that does not require segmentation of objects of interest, based on ensemble deep learning, is presented. Evaluation on publicly available datasets show that the proposed approach produced a model that recorded the best accuracy, sensitivity and specificity of 91.0%, 89.6% and 90.7% respectively.
Volume: 17
Issue: 2
Page: 1014-1020
Publish at: 2020-02-01

Investigation on EM radiations from interconnects in integrated circuits

10.12928/telkomnika.v18i1.13130
Lounas; University Mouloud Mammeri Belhimer , Arezki; Mouloud Mammeri University , Tizi-Ouzou. Algeria Benfdila , Ahcene; University Mouloud Mammeri Lakhlef
Characterization and estimation of interconnections behavior in integrated circuits design before the implementation phase is of paramount importance. This behavior seen as microstrip antennas gets complex as the internal signal (square or sine waves) frequencies increase. Thus, they become the preferred path for the propagation of electromagnetic disturbances. In this work we have worked out the numerical modeling of the electromagnetic interactions characterizing the electromagnetic compatibility in the microstrip transmission lines. The effect of these electromagnetic interactions in different structures topologies are studied through the analysis of the influence of the supply signals frequency and structures. The spacing between transmission line tracks and the number of tracks superposition is modeled. The evolution and variation of the scheme parameters in the frequency domain are determined. The transmission lines are considered parallel of equal spacing and superposed tracks of equal spacing and thickness. The capacitance and inductance matrices are computed and discussed. The results are found to comply with current research outcomes.
Volume: 18
Issue: 1
Page: 301-310
Publish at: 2020-02-01

A reliable next generation cyber security architecture for industrial internet of things environment

10.11591/ijece.v10i1.pp387-395
C. Vijayakumaran , B. Muthusenthil , B. Manickavasagam
Architectural changes are happening in the modern industries due to the adaption and the deployment of ‘Internet of Things (IoT)’ for monitoring and controlling various devices remotely from the external world. The most predominant place where the IoT technology makes the most sense is the industrial automation processes in smart industries (Industry 4.0). In this paper, a reliable ‘Next Generation Cyber Security Architecture (NCSA)’ is presented for Industrial IoT (IIoT) environment that detects and thwarts cybersecurity threats and vulnerabilities. It helps to automate the processes of exchanging real-time critical information between devices without any human intervention. It proposes an analytical framework that can be used to protect entities and network traffics involved in the IIoT wireless communication. It incorporates an automated cyber-defense authentication mechanism that detects and prevents security attacks when a network session has been established. The defense mechanism accomplishes the required level of security protection in the network by generating an identity token which is cryptographically encrypted and verified by a virtual gateway system. The proposed NCSA improves security in the IIoT environment and reduces operational management cost.
Volume: 10
Issue: 1
Page: 387-395
Publish at: 2020-02-01

RST invariant watermarking technique for vector map based on LCA-transform

10.12928/telkomnika.v18i1.15020
Saleh; King Abdulaziz University AL-ardhi , Vijey; King Abdulaziz University Thayananthan , Abdullah; King Abdulaziz University Basuhail
The dangers of copyright protection can impact 2D vector maps, having a knock-on effect on the use of vector data. To achieve invariance property, uniform RST (rotation, scaling and translation) and disguising the digital vector map’s information by implementing distortion control, is all done by using watermarking schemes. Convert an original map, then engrain the watermark. An LCA algorithm is used in this study, as a newly proposed way to protect the vector maps under copyright. The procedure is operated in this order: 1) use an original map, altered by the LCA algorithm, 2) use the coefficient of the transformation to engrain the watermark, inserting the resulting frequency into the LSB wave, 3) the watermarked map is acquired by using the inverse LCA map transformation. Further investigations discovered that the necessary standards of fidelity and invisibility can be achieved using this technique. This procedure also gives out numerous frequency domains for digital watermarking; as well as being resilient to signal and geometric invasions.
Volume: 18
Issue: 1
Page: 500-510
Publish at: 2020-02-01

Solving assembly line balancing problem using heuristic: a case study of power transformer in electrical industry

10.11591/ijeecs.v17.i2.pp850-857
Nurhanani Abu Bakar , Mohammad Fadzli Ramli , Mohd Zakimi Zakaria , Tan Chan Sin , Hafiz Masran
Currently, problem in assembly line has created so much attention, particularly in manufacturing area. Similar to this case study as they faced with problems regarding workstation in production line of electrical industry. There exist some cases where workstations in assembly line are experienced with bottleneck and suffered from high idle time. Thus, four heuristic methods are used for minimizing number or workstations and improve the bottleneck problems at the same time. In this case study, LCR, RPW and LPT have successfully minimized the number of workstations from 19 to 16. This solution has affected the layout of assembly line. Different from SPT that manage to improve the bottleneck among workstations by reducing number of workstations from 19 to 17 without changing the line layout. Therefore, both solution has brought an option for an engineer to choose which decision to be used in this assembly line in order to increase the line efficiency.
Volume: 17
Issue: 2
Page: 850-857
Publish at: 2020-02-01

Improved backtracking search optimization algorithm for PV/Wind/FC system

10.12928/telkomnika.v18i1.11887
Jihane; Mohammed V university in Rabat Kartite , Mohamed; Mohammed V university in Rabat Cherkaoui
This paper uses a novel optimization method based on the improved backtracking search optimization algorithm (IBSA). The study is conducted for a hybrid stand-alone system composed of photovoltaic panel (PV), wind turbine generator and fuel cell electrolyzer (FC). To demonstrate the effectiveness of the IBSA, four benchmark functions are used. The result shows the better exploration and exploitation of the improved backtracking search optimization algorithm in terms of convergence and speed for system comprinsing PV panel wind, turbine generator and fuel cell. The proposed algorithm is used to optimize the annual total cost (ATC) of the energy produced and feed up the load demand. The economic evaluation of the Hybrid PV/Wind/FC system is done throughout hourly demand and daily wind speed and insulation. The simulation results justify the robustness of the IBSA.
Volume: 18
Issue: 1
Page: 456-464
Publish at: 2020-02-01

Intelligent alarm system for hospitals using smartphone technology

10.12928/telkomnika.v18i1.13262
Bashar S.; Al-Nisour University College Bashar , Marwa M.; Al-Nisour University College Ismail
During the last decade, attention was paid to detect the accident and call the ambulance as soon as possible, the situation was neglected after the arrival of the patient to the specified service point. This negligence led to an increase in the mortality rate, especially where the highest percentage of deaths occurred during the first hour after the accident. This highest Mortality can be avoided by providing proper health care after the arrival of the patient to the hospital, the proposed system reduces the rescue time after the arrival of a patient to the hospital, and it requires each hospital to be endowed with a reception model responsible for detecting and reporting accident situations to the emergency service. It was be found that there is an urgent need for a web-based hospital management system with a mobile web service to respond immediately to incidents in the event of an accident. This system utilizes the Android phone application to connect to the server for transferring the specified data to the hospital and it can be used for comprehensive accident analysis and management. In this paper, a combination of Android phone application, database, and visual studio 2012 was used to develop the system.
Volume: 18
Issue: 1
Page: 450-455
Publish at: 2020-02-01

A performance analysis for real-time flood monitoring using image-based processing

10.11591/ijeecs.v17.i2.pp793-803
Qianyu Zhang , Nattha Jindapetch , Rakkrit Duangsoithong , Dujdow Buranapanichkit
Nowadays, various image-based methods have been used in the area of monitoring. Whereas the precision of detection objects and real-time processing are the key issues for many applications. Considering the limitation of the working environment, the higher correctness and faster operating time can guarantee the work efficiency. In this paper, the image-based methods have been studied to monitoring the state of the flood in the real-time system. The performance of each image processing technique has been evaluated based on accuracy and processing time. In the flood monitoring system, the variation of important parameters can cause the change of performance and the effect of the variable parameters has been demonstrated from the experiment results. After comparing to the other image-based techniques, canny edge detection presents the best one, which also has better repeatability with the source image from different locations. Consequently, the improved canny edge detection method has been proved that can work very well on the real hardware in the outdoor environment.
Volume: 17
Issue: 2
Page: 793-803
Publish at: 2020-02-01
1 2 3
...
1994 1995
Show 1189 of 1995

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