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

29,939 Article Results

Metaheuristic optimization in neural network model for seasonal data

10.12928/telkomnika.v19i6.20409
Budi; Diponegoro University Warsito , Rukun; Diponegoro University Santoso , Hasbi; Diponegoro University Yasin
The use of metaheuristic optimization techniques in obtaining the optimal weights of neural network model for the time series was the main part of this research. The three optimization methods used as experiments were genetic algorithm (GA), particle swarm optimization (PSO), and modified bee colony (MBC). Feed forward neural network (FFNN) was the neural network (NN) architecture chosen in this research. The limitations and weaknesses of gradient-based methods for learning algorithm inspired some researchers to use other techniques. A reasonable choice is non-gradient based method. Neural network is inspired by the characteristics of creatures. Therefore, the optimization techniques which are also resemble the patterns of life in nature will be appropriate. In this study, various scenarios on the three metaheuristic optimization methods were applied to get the best one. The proposed procedure was applied to the rainfall data. The experimental study showed that GA and PSO were recommended as optimization methods at FFNN model for the rainfall data.
Volume: 19
Issue: 6
Page: 1892-1901
Publish at: 2021-12-01

Optimal sizing and sitting of electric vehicle charging station by using archimedes optimization algorithm technique

10.11591/ijpeds.v12.i4.pp2557-2569
Mohamed Abdelhamed Zaki , Tarek Mahmoud , Mohamed Atia , EL Said Abd El Aziz Osman
Increasing penetration of electric vehicle (EV) load into the electricity sector will result in generation imbalance, an increase in real power loss, a low voltage profile and consequently a decrease in the margin of stability of voltage. It is necessary for the coordination of charging stations (CSs) for EV at the relevant locations to minimize the effect of increased EV load penetration in radial systems. In this paper, a new optimization method named Archimedes optimization algorithm (AOA) is proposed; it determined the optimal location and size for EV-CS for reducing power losses and improved voltage profile. In this work we used the photovoltaic (PV) renewable source as a main feeder for the CSs. Many of Artificial Intelligence technique are applied to determine the optimal sizing and sitting of EV-CSs considering the objective of minimization of real power loss. IEEE 33-bus testing network conducts simulation tests. The results highlighted the need to refine the EV-CS allocation to improve the performance. The ability to solve complex, non-linear objective optimization issues using AOA and to compare the results with other algorithms, namely particle swarm optimization (PSO), cuckoo search algorithm (CSA), shows its effectiveness in minimizing the power loss as required.
Volume: 12
Issue: 4
Page: 2557-2569
Publish at: 2021-12-01

An approach to partial occlusion using deep metric learning

10.11591/ijict.v10i3.pp204-211
Chethana Hadya Thammaiah , Trisiladevi Chandrakant Nagavi
The human face can be used as an identification and authentication tool in biometric systems. Face recognition in forensics is a challenging task due to the presence of partial occlusion features like wearing a hat, sunglasses, scarf, and beard. In forensics, criminal identification having partial occlusion features is the most difficult task to perform. In this paper, a combination of the histogram of gradients (HOG) with Euclidean distance is proposed. Deep metric learning is the process of measuring the similarity between the samples using optimal distance metrics for learning tasks. In the proposed system, a deep metric learning technique like HOG is used to generate a 128d real feature vector. Euclidean distance is then applied between the feature vectors and a tolerance threshold is set to decide whether it is a match or mismatch. Experiments are carried out on disguised faces in the wild (DFW) dataset collected from IIIT Delhi which consists of 1000 subjects in which 600 subjects were used for testing and the remaining 400 subjects were used for training purposes. The proposed system provides a recognition accuracy of 89.8% and it outperforms compared with other existing methods.
Volume: 10
Issue: 3
Page: 204-211
Publish at: 2021-12-01

A new approach to three-phase asynchronous motor model for electric power system analysis

10.11591/ijpeds.v12.i4.pp2083-2094
Laura Collazo Solar , Angel A. Costa Montiel , Miriam Vilaragut Llanes , Vladimir Sousa Santos
In this paper, a new steady-state model of a three-phase asynchronous motor is proposed to be used in the studies of electrical power systems. The model allows for obtaining the response of the demand for active and reactive power as a function of voltage and frequency. The contribution of the model is the integration of the characteristics of the mechanical load that can drive motors, either constant or variable load. The model was evaluated on a 2500 kW and 6000 V motor, for the two types of mechanical load, in a wide range of voltage and frequency, as well as four load factors. As a result of the evaluation, it was possible to verify that, for the nominal frequency and voltage variation, the type of load does not influence the behavior of the powers and that the reactive power is very sensitive to the voltage variation. In the nominal voltage and frequency deviation scenario, it was found that the type of load influences the behavior of the active and reactive power, especially in the variable load. The results demonstrate the importance of considering the model proposed in the simulation software of electrical power systems.
Volume: 12
Issue: 4
Page: 2083-2094
Publish at: 2021-12-01

Fatigue mitigation of wind turbine system using multiple point model predictive control

10.11591/ijpeds.v12.i4.pp2261-2272
Mutharasan Anburaj , Chandrasekar Perumal
A multi-point model predictive control (MPMPC) is widely used for many applications, including wind energy system (WES), notably enhanced power characteristics and oscillation regulation. In this work, MPMPC is adapted to condense the fatigue load of the WES and improve the lifetime of the turbine assembly. The lifetime examination is carried out by considering the three chief parameters: basic lifetime until failure, short-time damage equivalent loads (DELs), and lifetime DELs. The simulation study is performed for two cases: blade root bending moments and tower top bending. Further, fatigue load examination is demonstrated to analyze the effectiveness of the proposed controller. The observed results show that the lifetime analysis of the wind turbine system displayed more excellent characteristics, i.e., 49.50% greater than MPC. Also, the fatigue load mitigation showed greater magnitude due to the control action of the proposed controller, about 37.38% grander than MPC. Therefore, the attained outcomes exhibit outstanding performance compared with conventional controllers.
Volume: 12
Issue: 4
Page: 2261-2272
Publish at: 2021-12-01

Eco-design of portable solar-powered telescopic lamp for off-grid areas in Indonesia

10.11591/ijpeds.v12.i4.pp2511-2522
Kadek Heri Sanjaya , Ahmad Rajani , Hendri Maja Saputra , Dalmasius Ganjar Subagio , Ridwan Arief Subekti , Ahmad Fudholi
This study describes the development of eco-design of portable solar-powered telescopic lamp for off-grid area in Indonesia. Several design requirements for the lamp, namely, sustainability, portability, affordability, and reliability, are the objectives of the design process in this study. Sustainability is achieved through renewable energy and the application of eco-design principles. Portability means it is lightweight, compact and can be carried anywhere inside a tube. This solar-powered telescopic lamp was designed with a 3.7 V, 15.6 Ah battery power specification such that the battery power is around 57.72 Wh. The optimal use of the battery is 80% of the total battery power that is 46.176 Wh. With a power of 46,176 Wh, the battery can turn on the LED strip light with a 4.8 W power specification for 9.62 h. The test results showed that the telescopic lamp endurance met the expected specifications. The real consumed power by the LED strips was around 1.9 W. The charging test using solar panels with 12 Wp specifications showed that it will be fully charged in around 3.8 h. However, the performance of the telescopic lamp, especially in the charging process, is affected by the environment condition, such as sunlight intensity, ambient temperature, and humidity.
Volume: 12
Issue: 4
Page: 2511-2522
Publish at: 2021-12-01

New extensions of Rayleigh distribution based on inverted-Weibull and Weibull distributions

10.11591/ijece.v11i6.pp5107-5118
Mahmoud M. Smadi , Mahmoud H. Alrefaei
The Rayleigh distribution was proposed in the fields of acoustics and optics by lord Rayleigh. It has wide applications in communication theory, such as description of instantaneous peak power of received radio signals, i.e. study of vibrations and waves. It has also been used for modeling of wave propagation, radiation, synthetic aperture radar images, and lifetime data in engineering and clinical studies. This work proposes two new extensions of the Rayleigh distribution, namely the Rayleigh inverted-Weibull (RIW) and the Rayleigh Weibull (RW) distributions. Several fundamental properties are derived in this study, these include reliability and hazard functions, moments, quantile function, random number generation, skewness, and kurtosis. The maximum likelihood estimators for the model parameters of the two proposed models are also derived along with the asymptotic confidence intervals. Two real data sets in communication systems and clinical trials are analyzed to illustrate the concept of the proposed extensions. The results demonstrated that the proposed extensions showed better fitting than other extensions and competing models.
Volume: 11
Issue: 6
Page: 5107-5118
Publish at: 2021-12-01

A new method for vehicles detection and tracking using information and image processing

10.11591/ijece.v11i6.pp4942-4949
Mazouzi Amine , Kerfa Djoudi , Ismail Rakip Karas
In this article, a new method of vehicles detecting and tracking is presented: A thresholding followed by a mathematical morphology treatment are used. The tracking phase uses the information about a vehicle. An original labeling is proposed in this article. It helps to reduce some artefacts that occur at the detection level. The main contribution of this article lies in the possibility of merging information of low level (detection) and high level (tracking). In other words, it is shown that many artefacts resulting from image processing (low level) can be detected, and eliminated thanks to the information contained in the labeling (high level). The proposed method has been tested on many video sequences and examples are given illustrating the merits of our approach.
Volume: 11
Issue: 6
Page: 4942-4949
Publish at: 2021-12-01

Energy saving analysis of air fan motor in power plant boiler controlled by variable frequency drive

10.11591/ijpeds.v12.i4.pp2059-2069
Pramono Mukti Wibowo , Muhamad Haddin , Arief Marwanto
A reporting of Energy Audit in 2018 by LEMTEK UI has reported that air fan system currently used in Power Plant of PLTU Tanjung Jati B Jepara is inefficient, energy efficiency in FDF is only 32% and PAF efficiency is 49.01%. Inefficiency of the air fan system is an impacted there are waste of electric energy amount of 13,352,929 KWh (13,35 GWh) a year with a financial loss of IDR 13,352,929,140. To overcome this condition, variable frequency drive (VFD) is installed which adjusted air flow as needed so that energy waste can be reduced. MATLAB simulation is proposed to analyze the VFD method. The result shows that by using VFD, 8,233,573.444 KWh (8.45 GWh) can be saved a year. Total cost benefits are IDR 8,233,573,444 as 32.1% of saving cost. Efficiency of FDF is 72.57 % and PAF is 66.84%.
Volume: 12
Issue: 4
Page: 2059-2069
Publish at: 2021-12-01

The efficacy of multimodal intervention program on mental health states

10.11591/ijphs.v10i4.20833
Helena Baldonado Florendo , Joseph V. del Rosario
Filipino youths are the hope of Philippine society. However, cigarette smoking and binge drinking continually corrupt this aspiration. Mental health states interplay with the growing setback of substance consumption. The main objective of the study is to determine the efficacy of the multimodal intervention program among the participants in this study.  Specifically, it answers the following objectives: i) Develop an intervention program to address the high anxiety, mild depression, and normal self-esteem of the participants and ii) Determine the significant difference between the control group and the experimental group in the pre-test and post-test intervention measures. A matched-group experimental design was carried out among the participants who were randomly assigned to the control group and the experimental group.  There were forty participants who met the criteria set by the researchers.  When the multimodal intervention program was tested using t-test to analyze the findings at .05 level, it yielded significant results. Based on the findings of the study, the developed multimodal intervention program appeared to be effective. A follow-up study may be conducted to further test the efficacy.
Volume: 10
Issue: 4
Page: 785-792
Publish at: 2021-12-01

Amazigh part-of-speech tagging with machine learning and deep learning

10.11591/ijeecs.v24.i3.pp1814-1822
Otman Maarouf , Rachid El Ayachi , Mohamed Biniz
Natural language processing (NLP) is a part of artificial intelligence that dissects, comprehends, and changes common dialects with computers in composed and spoken settings. At that point in scripts. Grammatical features part-of-speech (POS) allow marking the word as per its statement. We find in the literature that POS is used in a few dialects, in particular: French and English. This paper investigates the attention-based long short-term memory (LSTM) networks and simple recurrent neural network (RNN) in Tifinagh POS tagging when it is compared to conditional random fields (CRF) and decision tree. The attractiveness of LSTM networks is their strength in modeling long-distance dependencies. The experiment results show that LSTM networks perform better than RNN, CRF and decision tree that has a near performance.
Volume: 24
Issue: 3
Page: 1814-1822
Publish at: 2021-12-01

New proposed fractional-polynomial functions: new recommendation for overcome the imbalance in three-phase systems

10.11591/ijpeds.v12.i4.pp2243-2250
Q. S. Vu , Bui Vu Minh , Minh Tran , N.V. Korovkin
Non-linear loads or load imbalances, etc., are the typical causes of asymmetric operation of three-phase systems. The appearance of inverse (positive) and homopolar (zero) symmetric components cause damage to the systems and electrical equipment and increase the power losses on the transmission lines. Reactive power compensation is one of the solutions that can overcome this asymmetry. The difficulty that exists in many different methods is the optimal calculation of the value of the compensator. In this paper, a new method to overcome these problems is proposed and investigagted. The proposed method is based on the fundamental electrical quantities (voltages and currents) on the controllable values of the static compensation devices and overcoming of the asymmetric operation regime in the three-phase systems.
Volume: 12
Issue: 4
Page: 2243-2250
Publish at: 2021-12-01

Lifestyle breast cancer patients among Indonesian women: A nationwide survey

10.11591/ijphs.v10i4.20913
Solikhah Solikhah , Khairunnisaa Nuur Aliifah Setyawati , Monthida Sangruangake
Recently, cancer is a major health problem in the world. Lifestyle changes and growing urbanization likely led to increasing breast cancer incidence in such in Indonesia. Therefore, this study aimed to explore lifestyle breast cancer patients among Indonesian women. The investigation was a cross-sectional study distributed among 3,392 females drawn from 13 out of 27 provinces in Indonesia. Multiple binary logistic regressions were conducted to investigate breast cancer risk among Indonesian. A significance level of 0.05 was employed in all analysis. Of the 3,392 respondents included in the analysis, more than half (52.71%; n=1,788) was aged 40–49 years old. The most common marital status of the participants was married (98.20%; n=3,331), followed by no smoking (94.69%; n=3,212) and active exercise (62.12%; n=2,107). Education level was significantly associated with breast cancer (AdjOR_Junior high school=0.21; 95%CI=0.06 to 0.70; p<0.01 and AdjOR_senior high school=0.60; 95%CI=0.15 to 2.26; p<0.05). Education level was significantly related to breast cancer. Lifestyle such as smoking and physical activity was suspected to affect breast cancer indirectly.
Volume: 10
Issue: 4
Page: 730-734
Publish at: 2021-12-01

Emotion recognition from syllabic units using k-nearest-neighbor classification and energy distribution

10.11591/ijece.v11i6.pp5438-5449
Abdellah Agrima , Ilham Mounir , Abdelmajid Farchi , Laila Elmaazouzi , Badia Mounir
In this article, we present an automatic technique for recognizing emotional states from speech signals. The main focus of this paper is to present an efficient and reduced set of acoustic features that allows us to recognize the four basic human emotions (anger, sadness, joy, and neutral). The proposed features vector is composed by twenty-eight measurements corresponding to standard acoustic features such as formants, fundamental frequency (obtained by Praat software) as well as introducing new features based on the calculation of the energies in some specific frequency bands and their distributions (thanks to MATLAB codes). The extracted measurements are obtained from syllabic units’ consonant/vowel (CV) derived from Moroccan Arabic dialect emotional database (MADED) corpus. Thereafter, the data which has been collected is then trained by a k-nearest-neighbor (KNN) classifier to perform the automated recognition phase. The results reach 64.65% in the multi-class classification and 94.95% for classification between positive and negative emotions.
Volume: 11
Issue: 6
Page: 5438-5449
Publish at: 2021-12-01

Performance improvement of the variable speed wind turbine driving a DFIG using nonlinear control strategies

10.11591/ijpeds.v12.i4.pp2470-2482
Chojaa Hamid , A. Derouich , T. Hallabi , O. Zamzoum , M. Taoussi , S. Rhaili , O. Boulkhrachef
In this research paper, a nonlinear Backstepping controller has been proposed in order to improve the dynamic performance of a doubly fed induction generator (DFIG) based Wind Energy conversion System, connected to the grid through a back-to-back converter. Firstly, an overall modeling of proposed system has been presented. Thereafter, three control techniques namely backstepping (BSC), sliding mode (SMC) and field-oriented control (FOC) using a conventional PI regulator have been designed in order to control the stator active and reactive powers of the DFIG. In addition, the maximum power point tracking (MPPT) strategy has been investigated in this work with three mechanical speed controllers: BSC, SMC and PI controller with the aim of making a synthesis and a comparison between their performances to determine which of those three techniques is more efficient to extract the maximum power. Finally, a thorough comparison between the adopted techniques for the DFIG control has been established in terms of response time, rise time, total harmonic distortion THD (%) of the stator current, static errors and robustness. The effectiveness and robustness of each control approach has been implemented and tested under MATLAB/Simulink environment by using a 1.5 MW wind system model.
Volume: 12
Issue: 4
Page: 2470-2482
Publish at: 2021-12-01
1 2 3
...
1995 1996
Show 872 of 1996

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