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

Artificial neural network forecasting performance with missing value imputations

10.11591/ijai.v9.i1.pp33-39
Nur Haizum Abd Rahman , Muhammad Hisyam Lee
This paper presents time series forecasting method in order to achieve high accuracy performance. In this study, the modern time series approach with the presence of missing values problem is developed. The artificial neural networks (ANNs) is used to forecast the future values with the missing value imputations methods used known as average, normal ratio and also the modified method. The results are validated by using mean absolute error (MAE) and root mean square error (RMSE). The result shown that by considering the right method in missing values problems can improved artificial neural network forecast accuracy. It is proven in both MAE and RMSE measurements as forecast improved from 8.75 to 4.56 and from 10.57 to 5.85 respectively. Thus, this study suggests by understanding the problem in time series data can produce accurate forecast and the correct decision making can be produced.
Volume: 9
Issue: 1
Page: 33-39
Publish at: 2020-03-01

Veins projection performance based on ultrasonic distance sensor in various surface objects

10.11591/ijeecs.v17.i3.pp1362-1370
I Putu Adi Surya Gunawan , Riyanto Sigit , Agus Indra Gunawan
Intravenous therapy aims to inject fluids such as medicine or nutritions into the body via vein vessel. This procedure is needed in various cases whether in an ordinary or emergency. Every person has a different difficulty level thus a nurse usually encountered a problem when locating the position of vein vessel. A visualization device that able to work in realtime and have high mobility is really necessary for an emergency situation to speed up the intravenous access. In this study, a stand-alone veins visualization system was developed. The back-projection method that can adjust based on distance was used to speed up the visualization process. The distance between the device and the object is obtained by an ultrasonic distance sensor. The results of this projection method with a flat surface have maximum shift of 0.48 mm. While on various surfaces, projection shifts under 0.9 mm reach 89% from 140 measurement points. Projection shifts that reach more than 0.9 mm occurred due to the sensor readings are on steep curvature or large angles between segments and sensors.
Volume: 17
Issue: 3
Page: 1362-1370
Publish at: 2020-03-01

Solving optimal generation scheduling problem of microgrid using teaching learning based optimization algorithm

10.11591/ijeecs.v17.i3.pp1632-1638
Surender Reddy Salkuti
This paper proposes a new optimal scheduling methodology for a Microgrid (MG) considering the energy resources such as diesel generators, solar photovoltaic (PV) plants, wind farms, battery energy storage systems (BESSs), electric vehicles (EVs) and demand response (DR). The penetration level of renewable and sustainable energy resources (i.e., wind, solar PV energy, geothermal and ocean energy) in power generation systems is increasing. In this work, the EVs and storage are used as flexible DR sources and they can be combined with DR to improve the flexibility of MG. Various uncertainties exist in the MGs due to the intermittent/uncertain nature of renewable energy resources (RERs) such as wind and solar PV power outputs. In this paper, these uncertainties are modeled by using the probability analysis. In this paper, the optimal scheduling problem of MG is solved by minimizing the total operating cost (TOC) of MG. The TOC minimization objective is formulated by considering the cost due to power exchange between main grid and MG, diesel generators, wind, solar PV units, EVs, BESSs, and DR. The successful implementation of optimal scheduling of MG requires the widespread use of demand response and EVs. In this paper, teaching-learning-based optimization (TLBO) algorithm is used to solve the proposed optimization problem. The simulation studies are performed on a test MG by considering all the components of MG.
Volume: 17
Issue: 3
Page: 1632-1638
Publish at: 2020-03-01

Detection of cardiac sounds components: a pilot study

10.11591/ijeecs.v17.i3.pp1330-1337
Norezmi Jamal , Nabilah Ibrahim , MNAH Sha’abani , Zulkifli Taat
This paper presents a preliminary study related to the detection and identification of cardiac sounds components including first sound (S1), second sound (S2) and murmurs. Detection and identification of cardiac sounds are an important process in automated cardiac sound analysis system in order to automatically diagnose people who are having cardiovascular disorder and determine the existence of murmurs. Sixteen of recorded cardiac sounds (eight normal cardiac sounds, four abnormal cardiac sounds with systole murmur, and four abnormal cardiac sounds with diastole murmur) from PASCAL Classifying Heart Sounds Challenge database were examined for analysis. This work is significant in studying the time and time-frequency based detection of cardiac sounds components characteristics. In time-based analysis, envelope of signal energy was used to do the peak detection of S1, S2 and murmur and also analysis of cardiac cycle, systole and diastole duration. While time-frequency based analysis was used to determine the S1, S2 and murmur frequency range. The findings yield the overall accuracy of envelope-based detection for normal cardiac sound signal at 60.85% while for abnormal cardiac sound signal at 57.24%.
Volume: 17
Issue: 3
Page: 1330-1337
Publish at: 2020-03-01

Qualitative doctoral research in educational settings: Reflecting on meaningful encounters

10.11591/ijere.v9i1.20360
Myria Pieridou , Maria Kambouri-Danos
In qualitative doctoral research the methodological approach, and the research design are extremely important when ensuring the rigorousness of the work. This is particularly significant for all researchers, and even more for doctoral students who are still developing their research and analytical skills. This paper aims to support doctoral students in their research journey by highlighting some of the tensions involved in conducting qualitative research by unpicking the experiences of two doctoral students to learn from the concerns, questions and reflections on the use of qualitative methodology in their doctoral research projects. The findings reveal challenges and insights with regards to reflection, educational research and the developing identity of being a researcher. The paper discusses these reflections to support and guide doctoral students as early career researchers when planning and conducting qualitative research in educational settings. 
Volume: 9
Issue: 1
Page: 21-31
Publish at: 2020-03-01

Islamic economic development in Indonesian Islamic higher education

10.11591/ijere.v9i1.20317
Hamzah Hamzah , Agus Yudiawan , St. Umrah , Hasbullah Hasbullah
This study aims to explore how changes in community preferences, shari’ah economic development through the tridharma of higher education and its contribution to the development of shari’ah economics. This study was conducted at the UIN Alauddin Makassar, South Sulawesi, Indonesia. This study applied library research. Data collection techniques in this study using discourse from books, articles, magazines, journals, and web (internet). Furthermore, the data were analyzed using the Miles and Huberman model, among others, data reduction, data display and conclusion. The results show that there is a change in community preferences caused by external factors (changes in the social and economic environment) and internal factors in higher education in responding to community dynamics. Higher education can be used as a vehicle in the development of shari’ah Economy through the application of higher education tridharma. Furthermore, higher education also takes a significant role in developing scientific aspects and human resources in the field of Sharia Economics in Indonesia.
Volume: 9
Issue: 1
Page: 77-82
Publish at: 2020-03-01

Islanding detection of integrated distributed generation with advanced controller

10.11591/ijeecs.v17.i3.pp1626-1631
J Rajesh Reddy , A Pandian , R Dhanasekaran , Rami Reddy Ch , B Prasanna Lakshmi , B Neelima Devi
Grid integration of non conventional energy resources is increasing in day to day life to supply the global energy utilization requirement. The major problem with such integrated Distributed Generation (DG) is islanding. The islanding is originated in the integrated system when a part of the power system is disconnected from the grid and continue to feed the local load. The islanding is not safe to field persons and equipment. As per IEEE 1547 standards, the islanding should be detected within 2 seconds with the equipments associated with it. In this paper, a new islanding detection method is proposed with fuzzy rule based approach with inputs as the change in frequency and power. This method classifies the islanding and non islanding events efficiently compared to other passive methods. The simulations are carried on Matlab/ Simulink 2018b environment.
Volume: 17
Issue: 3
Page: 1626-1631
Publish at: 2020-03-01

Literation movement for leading schools: Best practice and leadership power

10.11591/ijere.v9i1.20279
Zalik Nuryana , Agus Suroyo , Indah Nurcahyati , Farid Setiawan , Arif Rahman
The school literacy movement is the first step of scientific development, aimed at enhancing science education. It has an important role in encouraging every citizen to have basic knowledge of the nature of science through active participation. This study aims to analyze the implementation of the School Literacy Movement program designated by the Ministry of Education and Culture due to the poor reading interest Indonesia students from several international surveys. The study was conducted at Al Mujahidin Muhammadiyah Middle School in Yogyakarta, using the qualitative method of data collection. The results show that the school literacy program is not only specific for reading and writing but for also other academics as activities such as numerals, science, digitalization, finance, culture, and citizenship. In conclusion, the implementation of a structured and systematic program positive impacts on the growth of literacy achievement for all school members from students, teachers, down to employees in Indonesia.
Volume: 9
Issue: 1
Page: 227-233
Publish at: 2020-03-01

Teaching workload in 21st century higher education learning setting

10.11591/ijere.v9i1.20419
Hamimah Ujir , Shanti Faridah Salleh , Ade Syaheda Wani Marzuki , Hashimatul Fatma Hashim , Aidil Azli Alias
A standard equation on teaching workload calculation in the previous academic setting only includes the contact hours with students through lecture, tutorial, laboratory and in-person consultation (i.e. one-to-one final year project consultation). This paper discusses teaching workload factors according to the current higher-education setting. Devising a teaching workload equation that includes all teaching and learning strategies in the 21st century higher education learning setting is needed. This is indeed a challenging task for the academic administrators to scrutinize every single parameter that accounted for teaching and learning. In this work, we have discussed the parameters which are significant in teaching workload calculation. For instance, the conventional in-person contact with the students, type of delivery, type of assessment, the preparation of materials for flipped classroom as well as MOOC, to name a few. Teaching workload also affects quality teaching and from the academic perception, the higher workload means lower-quality teaching.
Volume: 9
Issue: 1
Page: 221-226
Publish at: 2020-03-01

A malicious URLs detection system using optimization and machine learning classifiers

10.11591/ijeecs.v17.i3.pp1210-1214
Ong Vienna Lee , Ahmad Heryanto , Mohd Faizal Ab Razak , Anis Farihan Mat Raffei , Danakorn Nincarean Eh Phon , Shahreen Kasim , Tole Sutikno
The openness of the World Wide Web (Web) has become more exposed to cyber-attacks. An attacker performs the cyber-attacks on Web using malware Uniform Resource Locators (URLs) since it widely used by internet users. Therefore, a significant approach is required to detect malicious URLs and identify their nature attack. This study aims to assess the efficiency of the machine learning approach to detect and identify malicious URLs. In this study, we applied features optimization approaches by using a bio-inspired algorithm for selecting significant URL features which able to detect malicious URLs applications. By using machine learning approach with static analysis technique is used for detecting malicious URLs applications. Based on this combination as well as significant features, this paper shows promising results with higher detection accuracy.  The bio-inspired algorithm: particle swarm optimization (PSO) is used to optimized URLs features. In detecting malicious URLs, it shows that naïve Bayes and support vector machine (SVM) are able to achieve high detection accuracy with rate value of 99%, using URL as a feature.
Volume: 17
Issue: 3
Page: 1210-1214
Publish at: 2020-03-01

Optimization of artificial neural network topology for membrane bioreactor filtration using response surface methodology

10.11591/ijai.v9.i1.pp117-125
Syahira Ibrahim , Norhaliza Abdul Wahab , Fatimah Sham Ismail , Yahaya Md Sam
The optimization of artificial neural networks (ANN) topology for predicting permeate flux of palm oil mill effluent (POME) in membrane bioreactor (MBR) filtration has been investigated using response surface methodology (RSM). A radial basis function neural network (RBFNN) model, trained by gradient descent with momentum (GDM) algorithms was developed to correlate output (permeate flux) to the four exogenous input variables (airflow rate, transmembrane pressure, permeate pump and aeration pump). A second-order polynomial model was developed from training results for natural log mean square error of 50 developed ANNs to generate 3D response surfaces. The optimum ANN topology had minimum ln MSE when the number of hidden neurons, spread, momentum coefficient, learning rate and number of epochs were 16, 1.4, 0.28, 0.3 and 1852, respectively. The MSE and regression coeffcient of the ANN model were determined as 0.0022 and 0.9906 for training, 0.0052 and 0.9839 for testing and 0.0217 and 0.9707 for validation data sets. These results confirmed that combining RSM and ANN was precise for predicting permeates flux of POME on MBR system. This development may have significant potential to improve model accuracy and reduce computational time.
Volume: 9
Issue: 1
Page: 117-125
Publish at: 2020-03-01

ANN based method for improving gold price forecasting accuracy through modified gradient descent methods

10.11591/ijai.v9.i1.pp46-57
Shilpa Verma , G. T. Thampi , Madhuri Rao
Forecast of prices of financial assets including gold is of considerable importance for planning the economy. For centuries, people have been holding gold for many important reasons such as smoothening inflation fluctuations, protection from an economic crisis, sound investment etc.. Forecasting of gold prices is therefore an ever important exercise undertaken both by individuals and groups. Various local, global, political, psychological and economic factors make such a forecast a complex problem. Data analysts have been increasingly applying Artificial Intelligence (AI) techniques to make such forecasts. In the present work an inter comparison of gold price forecasting in Indian market is first done by employing a few classical Artificial Neural Network (ANN) techniques, namely Gradient Descent Method (GDM), Resilient Backpropagation method (RP), Scaled Conjugate Gradient method (SCG), Levenberg-Marquardt method (LM), Bayesian Regularization method (BR), One Step Secant method (OSS) and BFGS Quasi Newton method (BFG). Improvement in forecasting accuracy is achieved by proposing and developing a few modified GDM algorithms that incorporate different optimization functions by replacing the standard quadratic error function of classical GDM. Various optimization functions investigated in the present work are Mean median error function (MMD), Cauchy error function (CCY), Minkowski error function (MKW), Log cosh error function (LCH) and Negative logarithmic likelihood function (NLG). Modified algorithms incorporating these optimization functions are referred to here by GDM_MMD, GDM_CCY, GDM_KWK, GDM_LCH and GDM_NLG respectively. Gold price forecasting is then done by employing these algorithms and the results are analysed. The results of our study suggest that  the forecasting efficiency improves considerably on applying the modified methods proposed by us.
Volume: 9
Issue: 1
Page: 46-57
Publish at: 2020-03-01

Study of impact of art performance level of blue laser technology applications and its control

10.11591/ijeecs.v17.i3.pp1383-1389
Mohanad H. Ali , Mahmood H. Enad , Jasim Mohmed Jasim , Rawaa A. Abdul-Nab , Nadia Alani
In this work; we present an enhancement in blue laser diodes with new factors and applications for modern technology such as underwater telecommunications, bio-sensor and bio-medical systems etc. Years of advance meanwhile have much enhanced laser performance, and extremely improved their diversity, making lasers significant parts in scientific research, telecommunications, engineering, bio-medical imaging, materials working, and a swarm of other applications. This article viewing how laser technology has progressed to chance application requirements. The enhanced blue laser building diagrams to get a peak efficiency% at room temperature with modification. Moreover, we have as well estimated electro-optical performance packing of blue laser diodes been significantly various associated to GaAs laser method and novel developments and performances are required to enhance the optical power from anther laser diodes. Researchers need enhanced approaches to accurately make new the blue laser applications to use control of modern experimental measurements and optical communication.
Volume: 17
Issue: 3
Page: 1383-1389
Publish at: 2020-03-01

ARDUINO based accident prevention and auto intimation system

10.11591/ijeecs.v17.i3.pp1275-1280
Palanisamy R , PLS Sai Kumar , Mekala Paavan Kiran , Ashutosh Mahto , Md. Irfan , Maharishi Bhowmick
Often modern cars have a collision avoidance system built into them known as Pre-Crash System, or Collision Mitigation System in order to reduce the collision. But majority of vehicles on the road, especially heavy motor vehicles lack in such a system. In this paper, the implementation of the Collision Avoidance System is to reduce the risks of collisions at the hairpin bend on a Hilly track, Ghats, or other Zero visibility turns. The proposed system contains a set of IR sensors, LEDs, etc. It uses four IR sensors, which are placed on either side of the hairpin bend. The sensors are mutually exclusive and are connected to LEDs through wires. Based on the output of sensors, the LEDs will glow and start alerting the other vehicle approaching from the other end, Hence the drivers will decrease their speeds which would help in preventing collision. The LEDs will help the drivers in detecting the position of  the vehicles on either side of the bend. During climatic conditions like fog, snow, etc, the visibility of the drivers would decrease due to which they will not be able to see the LEDs, Hence, a collision may take place. To bring help as soon as possible to the injured, we have also made a proposed system which would alert the nearby hospitals that an accident has taken place. We have used Arduino UNO, GSM sim module and these will be kept inside a black box which will be inside the, car safe from breakage during the accident.
Volume: 17
Issue: 3
Page: 1275-1280
Publish at: 2020-03-01

Simplified down sampling factor based modified SVPWM technique for cascaded inverter fed induction motor drive

10.11591/ijaas.v9.i1.pp20-26
Ravi Kumar Bhukya , P. Satish Kumar
This paper presents a rivew, investigation and performance analysis of novel down samples factor based modified space vector PWM is called clamping SVPWM technique for cascaded Multilevel Invereter fed to Induction motor drive. In this paper the reference sine wave generated as in case of conventional off set injected SVPWM technique is modified by down sampling factor the reference wave by order of 10. The performance analyses of this modulation strategies are analyzed by apply for five level, seven level, nine level and eleven level inverter. The performance analysis of cascaded inverter interms of line voltage, stator current, speed, torque and total harmonic distortion. The results are depicting that PD PWM is more effective among the four proposed PWM technique. It is observed that the CSV Pulse width modulation ensures excellent, close to optimized pulse distribution results compared to SPWM technique and also 11-level inverter beter performance in case of low THD and better foundemental output voltages comapared to 5, 7, 9-level inverter. The proposed technique has been simulated using MATLAB/SIMULINK software. This proposed technique can be applied to N-level multilevel Inverter also.
Volume: 9
Issue: 1
Page: 20-26
Publish at: 2020-03-01
Show 1175 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