Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Filter Icon

Filters article

Years

FAQ Arrow
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

29,922 Article Results

Implementation of an incremental deep learning model for survival prediction of cardiovascular patients

10.11591/ijai.v10.i1.pp101-109
Sanaa Elyassami , Achraf Ait Kaddour
Cardiovascular diseases remain the leading cause of death, taking an estimated 17.9 million lives each year and representing 31% of all global deaths. The patient records including blood reports, cardiac echo reports, and physician’s notes can be used to perform feature analysis and to accurately classify heart disease patients. In this paper, an incremental deep learning model was developed and trained with stochastic gradient descent using feedforward neural networks. The chi-square test and the dropout regularization have been incorporated into the model to improve the generalization capabilities and the performance of the heart disease patients' classification model. The impact of the learning rate and the depth of neural networks on the performance were explored. The hyperbolic tangent, the rectifier linear unit, the Maxout, and the exponential rectifier linear unit were used as activation functions for the hidden and the output layer neurons. To avoid over-optimistic results, the performance of the proposed model was evaluated using balanced accuracy and the overall predictive value in addition to the accuracy, sensitivity, and specificity. The obtained results are promising, and the proposed model can be applied to a larger dataset and used by physicians to accurately classify heart disease patients.
Volume: 10
Issue: 1
Page: 101-109
Publish at: 2021-03-01

Ubiquitous learning in occupational health and safety for vocational education

10.11591/ijere.v10i1.20823
Ketut Ima Ismara , Amin Suharjono , Didi Supriadi
This research aimed to develop instructional media for occupational safety and health android-based for vocational schools. The second aim is to determine the feasibility of instructional media and student responses. The type of research is research and development (R&D) with the Analysis, Design, Development, Implementation, Evaluation (ADDIE) method, namely, analysis, design, development, implementation, and evaluation. The instrument used for data collection was a questionnaire with fourth scales. Data collection used an assessment questionnaire for two experts and 103 users. Research data analysis techniques used quantitative descriptive analysis. This study's results have produced products in the form of android-based instructional media for Occupational Safety and Health. In this study, we designed and developed an application called Zerosicks for mobile devices to help students learn occupational safety and health principles. The results of testing for all features and navigation work well and under their functions. The assessment results by content experts, media experts, and students as users indicate that this media has a very decent level of eligibility. Suggestions for product development are to add videos to the media, provide selected music, and add discussion forums for users.
Volume: 10
Issue: 1
Page: 285-292
Publish at: 2021-03-01

Impact of distributed generation on the Nigerian power network

10.11591/ijeecs.v21.i3.pp1263-1270
Taiwo Fasina , Bankole Adebanji , Adewale Abe , Isiaka Ismail
Distributed generations (DG) are being installed at increasing rates, both in developed and developing countries. The increasing number of DG connected to the distribution system could have a significant impact on the power system operation. This paper presents a case study investigating the impact of grid-connected DG on the Nigerian power network in terms of bus voltages and network losses. The results showed that without DG, some of the bus voltage magnitudes of the test system were outside the permissible voltage limit of 0.95pu≤Vi≤1.05p.u. However, with DG connected, the voltage magnitudes were improved to allowable values. The network active power loss was reduced by 12.03% from 85.60MW to 75.30MW. In this way, the power system becomes more efficient and secured.
Volume: 21
Issue: 3
Page: 1263-1270
Publish at: 2021-03-01

Design of a continuously and linearly controlled VSI-based STATCOM for load current balancing purposes

10.11591/ijpeds.v12.i1.pp183-198
Faris Asaad Abdulmunem , Abdulkareem Mokif Obais
In this paper, load current balancing are reviewed in both three-wire and 4-wire systems taking into account linearity, harmonics injection, and control schemes. A linearized static compensator (STATCOM) based on H-bridge voltage source inverter (VSI). The proposed STATCOM is controlled in closed loop mode via equipping it with a new current controller. The DC capacitor voltage of the STATCOM is kept constant without using external energy injection or storage devices via shunting the DC capacitor with a suitable series filter. The simulation results of the current responses of the 220V, 50Hz STATCOM reveal continuous and linear performance during responding to reactive current demands from 123A inductive current to 227A capacitive current. The transition time required for the proposed STATCOM during treatment of a sudden change in reactive current demand from maximum inductive current to maximum capacitive current is less than 40ms. The steady state portions of the STATCOM current responses show pure sinusoids, thus the proposed STATCOM can be promoted as harmonic free static Var compensator. The closed loop continuous mode control and the considerable linearity of the proposed STATCOM promot it as a bipolar susceptance (capacitive and inductive) in applications of load current balancing systems in both three and four wire power systems.
Volume: 12
Issue: 1
Page: 183-198
Publish at: 2021-03-01

Comparison and assessment of a different steel materials based on core losses reduction for three-phase induction motor

10.11591/ijpeds.v12.i1.pp29-40
Yaser Atta Yassin , Ali Nasser Hussain , Nagham Yassin Ahmed
This paper presents a core losses and performance calculation with different type of steel materials in the core design for three-phase induction motor by using "ANSYS Maxwell" program in order to identify the core material that provides the most effective performance by iron losses reduction. The coefficients of core losses are calculated from the magnetization curve and core Loss curve based on the on steel material databases. Although the difficult to obtain because of the little of existing information. Results show the capability of the proposed Cobalt steel (Hiperco 50) to achieve the significant losses reduction in comparison to the Electrical Steel NGO–AK Steel’s M-19 and Low Carbon Steel-SAE1020.
Volume: 12
Issue: 1
Page: 29-40
Publish at: 2021-03-01

SMUPI-BIS: a synthesis model for users’ perceived impact of business intelligence systems

10.11591/ijeecs.v21.i3.pp1856-1867
Intedhar Shakir Nasir , Ayad Hameed Mousa , Ihab L. Hussein Alsammak
Business intelligence is a collection of methodologies, methods, architectures, and technologies that convert raw data into significant and useful information used by organizations to enable more effective strategic, tactical, and operational insights and decision-making.  In spite of several studies have examined the critical success factors and development of business intelligence System, but few relevant studies have investigated perceptions of end-users Business Intelligence Systems. Furthermore, none of those studies was performed in a Higher Education Sector in Iraq. Consequently, the study aims to determine the business intelligence system features influencing perceived impact end users’ and of using business intelligence systems in Iraqi educational institutes. A technology acceptance model and technology organization environment framework were syntheses as a basis to develop a research model for business intelligence users' perceived impact and adopt of business intelligence systems named (SMUPI-BIS). Later, an online instrument (questionnaire) was designed to gather data from the business intelligence system users in five Iraqi universities. Twenty-one hypotheses were proposed and later tested. Then, for data analysis, the authors used several methods such as hierarchical regression, one-way ANOVA, descriptive statistics as well as structural equation modeling (SEM). The main outcomes of this study suggest that decision support, information quality, and real-time reporting are the most significant system characteristics influencing end users' perceived impact and their usage of business intelligence systems.
Volume: 21
Issue: 3
Page: 1856-1867
Publish at: 2021-03-01

Improving output current of inductor-cell based five-level CSI using hysteresis current controller

10.11591/ijpeds.v12.i1.pp249-257
Suroso Suroso , Winasis Winasis , Priswanto Priswanto , Sholikhah Sholikhah
Current source inverter (CSI) operates to output a specified ac current waveform from dc current sources. Talking about power quality, harmonics distortion of ac waveform is a problem of an inverter circuit. Generating a multilevel current waveform will have less harmonics content than a traditional three-level current waveform. In addition to non-ideal conditions of power switches, i.e. voltage drop in diodes, conductors or controlled switches, the performance of current controller applied in an inverter circuit will considerably affect the ac waveform quality produced by inverter circuit. This paper presents and discusses application of hysteresis current controller in the five-level H-bridge with inductor-cell current source inverter. The current controller performance was compared with the proportional integral current controller. Some test results are presented and discussed to explore the advantages of hysteresis controller in reducing the current ripple and harmonics distortion of output current.
Volume: 12
Issue: 1
Page: 249-257
Publish at: 2021-03-01

Off-grid rural electrification using integrated renewable energy sources

10.11591/ijaas.v10.i1.pp1-12
Fortune Chukwuebuka Amanze , Destiny Josiah Amanze
Presented in this study is an economic and technical evaluation to determine the optimal system combination for off-grid power generation based on solar, wind, and biodiesel renewable energy resource. Nsukka being endowed with high-intensity solar radiation, adequate wind speed, and sufficient bioresource is a prospective candidate for a hybrid system. The monthly average daily global radiation ranges from 3.91 kWh/m2 to 5.74 kWh/m2 and the average wind speed is about 2.64 m/s. This system was designed to meet the load requirement of the school with annual electrical demand of 10,163 MWh. Sensitivity analysis was carried out based on the effect of changes in biodiesel fuel price and interest rates on the economic performance criteria of the optimal configuration. The optimum hybrid system is composed of a 1 kW capacity PV system, an auto-sized biodiesel generator, and a battery bank of 820 h of autonomy. The levelized cost of energy from the optimal system was found to be $0.0898 per kWh based on sensitivity results. These results obtained show that an integrated system with the combination of PV, biodiesel generator, and battery bank is a cost-effective alternative to grid extension which cost $0.126 per kWh. The system's life span is for 25 years, and it is sustainable, economical, technically feasible, and environmentally friendly.
Volume: 10
Issue: 1
Page: 1-12
Publish at: 2021-03-01

The experimental identification method of the dynamic efficiency for frequency regulation algorithms of AEDs

10.11591/ijpeds.v12.i1.pp59-66
Vladimir L. Kodkin , Aleksandr S. Anikin
The article proposes and substantiates a method for studying the dynamics of an asynchronous electric drives with frequency control from the input side of the signal for setting the speed of rotation of the electric motor. In this method, a constant speed reference signal is added to a harmonic variable frequency signal. The set of amplitude changes and phase shifts of velocity oscillations are the initial data for identifying the dynamics of the studied control method. The logic of this method is determined by the previously obtained nonlinear transfer function of the link that forms the mechanical moment in the asynchronous electric drive with frequency control. Experiments have shown the dynamic benefits of the drive with positive stator current feedback.
Volume: 12
Issue: 1
Page: 59-66
Publish at: 2021-03-01

Design and simulation of Lidar based control system for wind turbine

10.11591/ijpeds.v12.i1.pp542-550
Atif Iqbal , Deng Ying , Faheem Akhter , Manoj Kumar Panjwani , Danish Khan
Renewable energy sources could be the main contributor to fulfilling the world’s energy requirement. Wind energy is grabbing the world’s attention due to its abundant nature and reliability. Wind energy is a prominent renewable energy source due to its availability and higher reliability. Despite the aforementioned benefits, there are some challenges such as wind measurement and prediction due to the turbulent nature of the wind. Lidar (light detection and ranging) technology is used in wind turbines to preview the wind and act it accordingly. Wind speed along with the direction is measured by the Lidar before it reaches the wind turbine plane and the control system of the wind turbine utilizes this data for optimal results. It enhances the control system along with it optimizes the output power. This paper presents the Lidar simulation model, which previews the wind earlier than the conventional feedback method. The Lidar simulation model is prepared and implemented on the horizontal axis wind turbine. The simulation is performed in GH Bladed at a 2.0 MW wind turbine. The output results are analyzed with the former method. The power extracted, pitch angle, rotor torque obtained from the proposed methodology proves its efficacy.
Volume: 12
Issue: 1
Page: 542-550
Publish at: 2021-03-01

Smart integration of drive system for induction motor applications in electric vehicles

10.11591/ijpeds.v12.i1.pp20-28
Mohamed K. Metwaly , Mohamed Alsharef , Nehmdoh A. Sabiha , Ehab E. Elattar , Ibrahim B. M. Taha , Amr M. Abd-Elhady , Nagy I. Elkalashy
In this paper, a smart drive system of the induction motor (IM) is proposed and adapted for applications in electric vehicles (EVs). Objectively, the EV drive systems are robust over wide speed and torque ranges. The proposed drive system is independent of encoder (encoderless) and concerned with the torque control drive (TCD) and indirect rotor field-oriented control (IRFOC) using the sliding mode observer (SMO). This arrangement of monitoring system and control techniques are smartly integrated for the IM applications in EVs. The encoderless technique utilizes SMO to estimate the stator current, rotor flux angle, and rotor speed. The SMO is verified in motoring mode at very low and zero speed conditions. The accelerator pedal is utilized for TCD to generate the reference torque required to accelerate the EV by the driver. The rotor flux angle is estimated based on IRFOC method. The laboratory waveforms illustrate the robustness of the encoderless control of the IM-based torque control drive system in electrical vehicle applications at very low speed using SMO. The laboratory waveforms prove the validity of SMO with encoderless control of a smart dive system of the IM in EV applications under load torque/speed variations.
Volume: 12
Issue: 1
Page: 20-28
Publish at: 2021-03-01

Grid to vehicle wireless power supply using single-phase matrix converter

10.11591/ijpeds.v12.i1.pp286-294
Muhamad Haziq Mohmad Akram , Rahimi Baharom
This paper presents the computer simulation model of a grid to vehicle (G2V) wireless power supply using a single-phase matrix converter (SPMC). The proposed system uses the SPMC that operates as a direct AC-AC converter to convert the supply frequency of 50 Hz to reach 20 kHz output frequency. The use of 20 kHz frequency is suitable for wireless power transfer (WPT) operation in order to obtain higher power transfer efficiency between the transmitter and the receiver parts. An advanced of the proposed circuit topology can solve the conventional system for G2V circuit topology that uses multiple stages of power conversion system, resulting in high power semiconductor losses that could lead to low efficiency. In this work, multiple stages of the conventional "AC-DC-AC" circuits have been reduced to a single power conversion stage by using the SPMC circuit topology. The use of the proposed circuit topology can reduce the number of devices, thus reduce the semiconductor losses. A part of reducing the semiconductor losses, the proposed circuit topology could also improve the power density and efficiency of the power supply system. A computer simulation model using MATLAB/Simulink has been developed to investigate the behavior of the proposed system. Selected simulation results are presented to verify the functionality of the proposed system.
Volume: 12
Issue: 1
Page: 286-294
Publish at: 2021-03-01

Virtual machine migration in MEC based artificial intelligence technique

10.11591/ijai.v10.i1.pp244-252
Ali OUACHA , Mohamed EL Ghmary
The whole world is inundated with smaller devices equipped with wireless communication interfaces. At the same time, the amount of data generated by these devices is becoming more important. The smaller size of these devices has the disadvantage of being short of processing and storage resources (memory, processes, energy,...), especially when it needs to process larger amounts of data. In order to overcome this weakness and process massive data, devices must help each other. A low-resource node can delegate the execution of a set of computionly heavy tasks to another machine in the network to process them for it. The machine with sufficient computational resources must also deposit the appropriate environment represented by the adapted virtual machine. Thus, in this paper, in order to migrate the virtual machine to an edge server in a mobile edge computing environment, we have proposed an approach based on artificial intelligence. More specifically, the main idea of this paper is to cut a virtual machine into several small pieces and then send them to an appropriate target node (Edge Server) using the ant colony algorithm. In order to test and prove the effectiveness of our approach, several simulations are made by NS3. The obtained results show that our approach is well adapted to mobile environments.
Volume: 10
Issue: 1
Page: 244-252
Publish at: 2021-03-01

The cascade methods of doubly-fed induction machine for generator system

10.11591/ijpeds.v12.i1.pp112-120
Diep-Dung Nguyen , Ngoc-Hoan Than , Duc-Tuan Hoang
This paper presents two solutions to cascade the doubly-fed induction machines in the power generator systems. The first solution is a traditional one with the power control circuit located on the stator-side. The second solution is a new one with the power control circuit located on the rotor-side. After analysis and evaluation, it is shown that the solution with the power control circuit located on the rotor side has advantages over the solution with the power control circuit located on the stator-side. Therefore, the authors chose the solution which is a power control circuit located on the rotor side to study, analyze in-depth and run the simulation. The results show that the proposed solution has a very good quality, the output voltage of the generator always follows the grid-voltage even when changing the gird-voltage or changing the speed of the generator.
Volume: 12
Issue: 1
Page: 112-120
Publish at: 2021-03-01

A high efficiency and high speed charge of Li-Ion battery charger interface using switching-based technique in 180 nm CMOS technology

10.11591/ijpeds.v12.i1.pp374-384
Mustapha El Alaoui , Fouad Farah , Karim El khadiri , Ahmed Tahiri , Rachid El Alami , Hassan Qjidaa
In this work, the design and analysis of new Li-Ion battery charger interface using the switching-based technique is proposed for high efficiency, high speed charge and low area. The high efficiency, the lower size area and the fast charge are the more important norms of the proposed Li-Ion battery charger interface. The battery charging is completed passes to each charging mode: The first mode is the trickle charge mode (TC), the second mode is the constant current mode (CC) and the last mode is the constant voltage mode (CV), in thirty three minutes. The new Li-Ion battery charger interface is designed, simulated and layouted in Cadence software using TSCM 180 nm CMOS technology. With an input voltage VIN = 4.5 V, the output battery voltage (VBAT) may range from 2.7 V to 4.2 V and the maximum charging battery current (IBAT) is 1.7 A. The peak efficiency reaches 97% and the total area is only 0.03mm2 .
Volume: 12
Issue: 1
Page: 374-384
Publish at: 2021-03-01
Show 998 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