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

An optimized approach for extensive segmentation and classification of brain MRI

10.11591/ijece.v10i3.pp2392-2401
Harish S , G.F Ali Ahammed
With the significant contribution in medical image processing for an effective diagnosis of critical health condition in human, there has been evolution of various methods and techniques in abnormality detection and classification process. An insight to the existing approaches highlights that potential amount of work is being carried out in detection and segmentation process but less effective modelling towards classification problems. This manuscript discusses about a simple and robust modelling of a technique that offers comprehensive segmentation process as well as classification process using Artificial Neural Network. Different from any existing approach, the study offers more granularities towards foreground/background indexing with its comprehensive segmentation process while introducing a unique morphological operation along with graph-believe network for ensuring approximately 99% of accuracy of proposed system in contrast to existing learning scheme.
Volume: 10
Issue: 3
Page: 2392-2401
Publish at: 2020-06-01

Knowledge and attitude about risky pregnancy among student

10.11591/ijere.v9i2.20413
Suci Musvita Ayu , S. Lindawati , Thoharoh Halimatusa’diyah
This study was conducted examine the effect of counseling on the increasing knowledge and attitudes about risky pregnancies at Muhammadiyah 1 Vocational High School in Wonosobo, Indonesia. This research was quasi-experimental research employed quasi experiment design with one group pretest-post-test design. Measurements were made before and after treatment, by doing a pre-test and post-test. Sample sie in this study was 108 students. The instrument in this study is the questionnaire. The results of the knowledge variable showed a significant value 0.003. There is an effect of reproductive health counseling on increasing knowledge and attitudes about risky.
Volume: 9
Issue: 2
Page: 326-334
Publish at: 2020-06-01

Optimal location of unified power flow controller genetic algorithm based

10.11591/ijpeds.v11.i2.pp886-894
Sana Khalid Abdul Hassan , Firas Mohammed Tuaimah
Now-a-days the Flexible AC Transmission Systems (FACTS) technology is very effective in improving the power flow along the transmission lines and makes the power system more flexible and controllable. This paper deals with overload transmission system problems such as (increase the total losses, raise the rate of power generation, and the transmission line may be exposed to shut down when the load demand increase from the thermal limit of transmission line) and how can solve this problem by choosing the optimal location and parameters of Unified Power Flow Controllers (UPFCs). which was specified based on Genetic Algorithm (GA) optimization method, it was utilized to search for optimum FACT parameters setting and location based to achieve the following objectives: improve voltages profile, reduce power losses, treatment of power flow in overloaded transmission lines and reduce power generation. MATLAB was used for running both the GA program and Newton Raphson method for solving the load flow of the system The proposed approach is examined and tested on IEEE 30-bus system. The practical part has been solved through Power System Simulation for Engineers (PSS\E) software Version 32.0 (The Power System Simulator for Engineering (PSS/E) software created from Siemens PTI to provide a system of computer programs and structured data files designed to handle the basic functions of power system performance simulation work, such as power flow, optimal power flow, fault analysis, dynamic simulations...etc.). The Comparative results between the experimental and practical parts obtained from adopting the UPFC where too close and almost the same under different loading conditions, which are (5%, 10%, 15% and 20%) of the total load. can show that the total active power losses for the system reduce at 69.594% at normal case after add the UPFC device to the system. also the reactive power losses reduce by 75.483% at the same case as well as for the rest of the cases. in the other hand can noted the system will not have any overload lines after add UPFC to the system with suitable parameters.
Volume: 11
Issue: 2
Page: 886-894
Publish at: 2020-06-01

Advanced control scheme of a unifiedpower flow controller using sliding mode control

10.11591/ijpeds.v11.i2.pp625-633
Abdellatif Hinda , Mounir Khiat , Zinelaabidine Boudjema
This paper presents an advanced control scheme based on sliding mode control of a unified power flow controller (UPFC). This controller can generate a number of benefits in terms of static and dynamic operation of the power system such as the control law is synthesized with two kinds of controllers: sliding mode controller (SMC), and proportional integral (PI). Their respective performances are compared in terms of reference monitoring, sensitivity to disturbances and robustness. We have to study the problem of controlling power in electric system by UPFC. The simulation results show the effectiveness of the proposed strategy especially in chattering-free behavior, response to sudden load variations and robustness. All the simulations for the above work have been carried out using MATLAB/Simulink. Various simulations have given very satisfactory results and we have successfully improved the active and reactive power flows on a line of transmission, as well as to control voltage at the bus where it is connected, the studies and illustrate the effectiveness and capability of UPFC in improving power.
Volume: 11
Issue: 2
Page: 625-633
Publish at: 2020-06-01

New concept for cryptographic construction design based on noniterative behavior

10.11591/ijai.v9.i2.pp229-235
Abdallah Abouchouar , Fouzia Omary , Khadija Achkoun
Nowadays, cryptography especially hash functions require to move from classical paradigms to an original concept able to handle security issues and new hardware architecture challenges as in distributed systems. In fact, most of current hash functions apply the same design pattern that was proved vulnerable against security threats; hence the impact of a potential weakness can be costly. Thus, the solution begins with a deep analysis of divers attack strategies; this way can lead to finding a new approach that enables new innovative and reliable candidates as alternative hash functions. So to achieve this goal, in this article we introduce a new construction design that consists of a non-iterative behavior by combining a parallel block processing and a sequential xor addition process, in order to provide a secure design without changing the expected goal of a hash function, at the same time avoid the use of vulnerable structures.
Volume: 9
Issue: 2
Page: 229-235
Publish at: 2020-06-01

A hybrid artificial neural network - genetic algorithm for load shedding

10.11591/ijece.v10i3.pp2250-2258
Le Trong Nghia , Quyen Huy Anh , Phung Trieu Tan , N Thai An
This paper proposes the method of applying Artificial Neural Network (ANN) with Back Propagation (BP) algorithm in combination or hybrid with Genetic Algorithm (GA) to propose load shedding strategies in the power system. The Genetic Algorithm is used to support the training of Back Propagation Neural Networks (BPNN) to improve regression ability, minimize errors and reduce the training time. Besides, the Relief algorithm is used to reduce the number of input variables of the neural network. The minimum load shedding with consideration of the primary and secondary control is calculated to restore the frequency of the electrical system. The distribution of power load shedding at each load bus of the system based on the phase electrical distance between the outage generator and the load buses. The simulation results have been verified through using MATLAB and PowerWorld software systems. The results show that the Hybrid Gen-Bayesian algorithm (GA-Trainbr) has a remarkable superiority in accuracy as well as training time. The effectiveness of the proposed method is tested on the IEEE 37 bus 9 generators standard system diagram showing the effectiveness of the proposed method.
Volume: 10
Issue: 3
Page: 2250-2258
Publish at: 2020-06-01

Bluetooth embedded digital ammeter with android app data logging

10.11591/ijeecs.v18.i3.pp1400-1407
Chin Fhong Soon , Boon Huei Teng , Kian Sek Tee , Siat Ling Jong , Mohd Khairul Ahmad , Marlia Morsin , Tiong Hin Ong
Monitoring current supplies to light emitting diode (LED) luminaires is one of the reliability tests performed manually. Bluetooth (HC-05) embedded digital ammeter was proposed to acquire currents of a badge of LED products and hence, quality can be assured. Android App was designed to remotely record the current supplies to the different models of LED products and checking if the current measured is within the allowed range. The current data can be further analysed to control the quality of the LED luminaires produced. The pass and fail-current range can be set in the digital ammeter for alerting abnormal current measured by the operator. Therefore, IOT embedded digital ammeter will help in monitoring data consistency of LED products and improve quality assurance procedure.
Volume: 18
Issue: 3
Page: 1400-1407
Publish at: 2020-06-01

A predictive model for network intrusion detection using stacking approach

10.11591/ijece.v10i3.pp2734-2741
Smitha Rajagopal , Poornima Panduranga Kundapur , Hareesh Katiganere Siddaramappa
Due to the emerging technological advances, cyber-attacks continue to hamper information systems. The changing dimensionality of cyber threat landscape compel security experts to devise novel approaches to address the problem of network intrusion detection. Machine learning algorithms are extensively used to detect intrusions by dint of their remarkable predictive power. This work presents an ensemble approach for network intrusion detection using a concept called Stacking. As per the popular no free lunch theorem of machine learning, employing single classifier for a problem at hand may not be ideal to achieve generalization. Therefore, the proposed work on network intrusion detection emphasizes upon a combinative approach to improve performance. A robust processing paradigm called Graphlab Create, capable of upholding massive data has been used to implement the proposed methodology. Two benchmark datasets like UNSW NB-15 and UGR’ 16 datasets are considered to demonstrate the validity of predictions. Empirical investigation has illustrated that the performance of the proposed approach has been reasonably good. The contribution of the proposed approach lies in its finesse to generate fewer misclassifications pertaining to various attack vectors considered in the study.
Volume: 10
Issue: 3
Page: 2734-2741
Publish at: 2020-06-01

Design and implement a new mechanism for audio, video and screen recording based on WebRTC technology

10.11591/ijece.v10i3.pp2773-2778
Naktal Edan , Sanabil A Mahmood
Many years ago, Flash was essential in browsers to interact with the user media devices, such as a microphone and camera. Today, Web Real-Time Communication (WebRTC) technology has come to substitute the flash, so browsers do not need the flash to access media devices or establish their communication. However, WebRTC standards do not express precisely how browsers can record audios, videos or screen instead of describing getUserMedia API that enables a browser to access microphone and camera. The prime objective of this research is to create a new WebRTC recording mechanism to record audios, videos, and screen using Google Chrome, Firefox, and Opera. This experiment applied through Ethernet and Wireless of the Internet and 4G networks. Also, the recording mechanism of this research was obtained based on JavaScript Library for audio, video, screen (2D and 3D animation) recording. Besides, different audio and video codecs in Chrome, Firefox and Opera were utilised, such as VP8, VP9, and H264 for video, and Opus codec for audio. Not only but also, various bitrates (100 bytes bps, 1 Kbps, 100 Kbps, 1 MB bps, and 1 GB bps), different resolutions (1080p, 720p, 480p, and HD (3840* 2160)), and various frame-rates (fps) 5, 15, 24, 30 and 60 were considered and tested. Besides, an evaluation of recording mechanism, Quality of Experience (QoE) through actual users, resources, such as CPU performance was also done. In this paper, a novel implementation was accomplished over different networks, different browsers, various audio and video codecs, many peers, opening one or multi browsers at the same time, keep the streaming active as much as the user needs, save the record, using only audio and/or video recording as conferencing with full screen, etc.
Volume: 10
Issue: 3
Page: 2773-2778
Publish at: 2020-06-01

A deep learning AlexNet model for classification of red blood cells in sickle cell anemia

10.11591/ijai.v9.i2.pp221-228
Hajara Aliyu Abdulkarim , Mohd Azhar Abdul Razak , Rubita Sudirman , Norhafizah Ramli
Sickle cell anemia (SCA) is a serious hematological disorder, where affected patients are frequently hospitalized throughout a lifetime and even can cause death. The manual method of detecting and classifying abnormal cells of SCA patient blood film through a microscope is time-consuming, tedious, prone to error, and require a trained hematologist. The affected patient has many cell shapes that show important biomechanical characteristics. Hence, having an effective way of classifying the abnormalities present in the SCA disease will give a better insight into managing the concerned patient's life. This work proposed algorithm in two-phase firstly, automation of red blood cells (RBCs) extraction to identify the RBC region of interest (ROI) from the patient’s blood smear image. Secondly, deep learning AlexNet model is employed to classify and predict the abnormalities presence in SCA patients. The study was performed with (over 9,000 single RBC images) taken from 130 SCA patient each class having 750 cells. To develop a shape factor quantification and general multiscale shape analysis. We reveal that the proposed framework can classify 15 types of RBC shapes including normal in an automated manner with a deep AlexNet transfer learning model. The cell's name classification prediction accuracy, sensitivity, specificity, and precision of 95.92%, 77%, 98.82%, and 90% were achieved, respectively.
Volume: 9
Issue: 2
Page: 221-228
Publish at: 2020-06-01

Single phase 21 level hybrid multilevel inverter with reduced power components employing low frequency modulation technique

10.11591/ijpeds.v11.i2.pp810-822
Sheikh Tanzim Meraj , Nor Zaihar Yahaya , Kamrul Hasan , Ammar Masaoud
This paper introduces a new hybrid topology of multilevel inverter capable of generating 21-level output voltage. The proposed topology is built using the combination of cross-switched bridge and a conventional full H-bridge. Compared to the conventional topologies and other hybrid topologies, the newly introduced multilevel inverter has the ability to maximize the number of voltage levels utilizing lower number of DC voltage sources, integrated bipolar transistor (IGBT) switches and gate drivers. A low frequency modulation technique is used to generate the ideal multilevel output voltage and gate pulses. Furthermore, the proposed topology is validated by building a hardware prototype and obtaining relevant experimental results. The acquired simulated and experimental results indicate the proper functioning of the proposed hybrid topology along with the compatibility of the applied modulation technique.
Volume: 11
Issue: 2
Page: 810-822
Publish at: 2020-06-01

Evolutionary algorithms based tuning of PID controller for an AVR system

10.11591/ijece.v10i3.pp3047-3056
Petchinathan Govindan
In this paper, an evolutionary algorithm based optimization algorithm is proposed with new objective function to design a PID controller for the automatic voltage regulator (AVR) system. The new objective function is proposed to improve the transient response of the AVR control system and to obtain the optimal values of controller gain. In this paper, particle swarm optimization (PSO) and cuckoo search (CS) algorithms are proposed to tune the parameters of a PID controller for the control of AVR system. Simulation results are capable and illustrate the effectiveness of the proposed method. Numerical and simulation results based on the proposed tuning approach on PID control of an AVR system for servo and regulatory control show the excellent performance of PSO and CS optimization algorithms.
Volume: 10
Issue: 3
Page: 3047-3056
Publish at: 2020-06-01

Modeling and simulation of DC to DC boost converter using single phase matrix converter topology

10.11591/ijpeds.v11.i2.pp774-784
Fajariah Kadir , S.Z. Mohammad Noor , Faranadia A.H. , K.S. Muhammad
The main objective of this work is to model and simulate DC to DC Boost Converter using Single Phase Matrix Converter (SPMC) topology using MATLAB/Simulink (MLS). The output voltage is controlled by using Pulse Width Modulation (PWM) technique. Four pairs of Insulated Gate Bipolar Transistor (IGBT) is used as the switching device where for each pair, it is located in parallel and opposite direction. Safe commutation technique is performed in preventing voltage spike at the output. Through the simulation, at switching frequency of 25kHz, the model is able to step up its input voltage about two times larger and all of the results achieved a good agreement with the principle of four quadrant operation. It is also realized that without the implementation of safe commutation technique, spikes were generated and the model is unable to boost its input voltage. All of the selected results from the analysis which includes variation of quadrant, switching frequency, duty cycle and resistive load are presented in this paper.
Volume: 11
Issue: 2
Page: 774-784
Publish at: 2020-06-01

Personal identity verification based ECG biometric using non-fiducial features

10.11591/ijece.v10i3.pp3007-3013
Marwa A. Elshahed
Biometrics was used as an automated and fast acceptable technology for human identification and it may be behavioral or physiological traits. Any biometric system based on identification or verification modes for human identity. The electrocardiogram (ECG) is considered as one of the physiological biometrics which impossible to mimic or stole. ECG feature extraction methods were performed using fiducial or non-fiducial approaches. This research presents an authentication ECG biometric system using non-fiducial features obtained by Discrete Wavelet Decomposition and the Euclidean Distance technique was used to implement the identity verification. From the obtained results, the proposed system accuracy is 96.66% also, using the verification system is preferred for a large number of individuals as it takes less time to get the decision.
Volume: 10
Issue: 3
Page: 3007-3013
Publish at: 2020-06-01

Design and implementation of variable and constant load for induction motor

10.11591/ijpeds.v11.i2.pp762-773
Salam Waley Shneen , Hashmia Sh. Dakheel , Zainab B. Abdulla
To design and implementation of variable and constant with no load for induction motor (IM) that is the goal in this work. This paper was including three parts, first the simulation model with no load for IM, Second the simulation model with constant load for IM, Third the simulation model with variable load for IM. In addition, this work includes comparative between two different controllers (PI and fuzzy logic control (FLC). The simulation results clearly the implementation of variable and constant with no load for IM. The simulation response of the system achieves better results when choosing to use type fuzzy-PI controller technique comparison with conventional PI controller and improve the performance of the system at different operation conditions.
Volume: 11
Issue: 2
Page: 762-773
Publish at: 2020-06-01
1 2 3
...
1994 1995
Show 1124 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