Digital Library

Featured New Articles

IJPHS

Early Access

Decision making power over reproductive health service utilization among married Ethiopian women: cross sectional study

Dessalegn Nigatu Rundasa, Zerihun Bayabil, Tarekegn Fekede,

Decision-making power of women is one of the essential factors which influence maternal health service utilization. Women's lack of decision over reproductive health service utilization affects their protection from unwanted childbearing, unsafe sex, and their consequences. To assess decision-making power on Reproductive Health service utilization and its associated factors among married women in South West Ethiopia, 2020. Cross-sectional study was conducted from May to July 2020 among 584 married women of the reproductive age. A total of 288 in urban and 288 in rural married women were interviewed and these yields a response rate of 98.6% both in urban and rural. Decision-making power over reproductive health service utilization in urban and rural was 55.2% [95% CI (52.7-64.6)] and 40.3% [95% CI (39.9-52.5)] respectively. In urban, being wives of government-employed spouses [AOR 2.102 95% CI (1.16, 3.81)], knowledge on RH [AOR 3.33, 95% CI (1.20, 12.49)], above five years in marriage [AOR 1.91, 95% CI (1.19,7.70)], were found to be predictors of women’s decision-making power over reproductive health use. The study revealed that in urban settings those women who had marriage duration five and more than five years, being wives of government-employed spouses had more likely decision-making power on reproductive health utilization but not in rural settings. Hence, reproductive health interventions in the area should be promoted by considering empowering married women on reproductive health service utilization.

10.11591/ijphs.v11i2.21276

IJPHS

Early Access

Maternal risk factors in stunting of children aged 24-59 months

Keke Susilowati Sholehah, Endang Sutedja, Hadyana Sukandar,

Stunting is a height that is not appropriate with the age, it is characterized by delayed growth of the child who results in failure to reach normal height. The high prevalence of stunting in the world, 14-17% of child mortality is caused by stunting. Pandeglang Regency, Indonesia is an area with the highest prevalence of stunting in Banten Province and the prevalence is 39.5%. The purpose of this study was to analyze the maternal risk factors that the most influence prevalence of stunting in children with aged 24-59 months in Pandeglang Regency, Banten Province, Indonesia. This research is an analytic observational study with a case control study design and using 200 respondents. The case group were mothers who had stunted children and the control group were mothers who had children with normal stature. Data obtained from filling out the mother's questionnaire include maternal and child health books. The results of multivariable analysis with multiple logistic regression found that close birth spacing ORadj (95% CI): 9.61 (1.16-79.56), nutritional status of pregnant women (KEK) ORadj: 4.37 (1.79-10.64), short mother's height was ORadj L: 2.38 (1.21-4.67) and preterm gestational age was ORadj: 1.98 (1.06-3.72) and Fe minimum consumption ORadj: 1.75 (0.94-3.26). Birth spacing are the most influential maternal risk factors for the prevalence of stunting in children aged 24-59 months. Long-term contraceptive methods such as IUDs and implants need to be held to increase long-term family planning acceptors so they can be more optimal in spacing pregnancies at least two years.

10.11591/ijphs.v11i2.20869

IJECE

Early Access

Analysis of the visualizing changes in radar time series using the REACTIV method through satellite imagery

Hamood Shehab Hamid, Raad Farhood Chisab,

A visualizing temporal stack of synthetic aperture radar (SAR) images are presented in this work, the method is called REACTIV, which enabled us to highlight color zones that have undergone change over the detected period of time. This work has been widely tested using Google Earth Engine (GEE) platform, this method depends on the hue-saturation-value (HSV) of visualizing space and supports estimation only in the time domain; the method does not support the spatial estimation. The coefficient of temporal coefficient variation is coded depending on the saturation color, of which several statistical properties are described. The limitations are studied, and some applications are implemented in this study.

10.11591/ijece.v12i4.pp%p

IJECE

Early Access

Spectral estimator effects on accuracy of speed-over-ground radar

Khairul Khaizi Mohd Shariff, Suraya Zainuddin, Noor Hafizah Abdul Aziz, Nur Emileen Abd Rashid, Nor Ayu Zalina Zakaria,

Spectral estimation is a critical signal processing step in speed-over-ground (SoG) radar. It is argued that, for accurate speed estimation, spectral estimation should use low bias and variance estimator. However, there is no evaluation on spectral estimation techniques in terms of estimating mean Doppler frequency to date. In this paper, we evaluate two common spectral estimation techniques, namely periodogram based on Fourier transformation and the autoregressive (AR) based on burg algorithm. These spectral estimators are evaluated in terms of their bias and variance in estimating a mean frequency. For this purpose, the spectral estimators are evaluated with different Doppler signals that varied in mean frequency and signal-to-noise ratio (SNR). Results in this study indicates that the periodogram method performs well in most of the tests while the AR method did not perform as well as these but offered a slight improvement over the periodogram in terms of variance.

10.11591/ijece.v12i4.pp%p

IJECE

Early Access

Fake news detection for Arabic headlines-articles news data using deep learning

Hassan Najadat, Mais Tawalbeh, Rasha Awawdeh,

Fake news has become increasingly prevalent in recent years. The evolution of social websites has spurred the expansion of fake news causing it to a mixture with truthful information. English fake news detection had the largest share of studies, unlike Arabic fake news detection, which is still very limited. Fake news phenomenon has changed people and social perspectives through revolts in several Arab countries. False news results in the distortion of reality ignite chaos and stir public judgments. This paper provides an Arabic fake news detection approach using different deep learning models including long short-term memory and convolutional neural network   based on article-headline pairs to differentiate if a news headline is in fact related or unrelated to the parallel news article. In this paper, a dataset created about the war in Syria and related to the Middle East political issues is utilized. The whole data comprises 422 claims and 3,042 articles. The models yield promising results.

10.11591/ijece.v12i4.pp%p

IJECE

Early Access

Breast cancer histological images nuclei segmentation and optimized classification with deep learning

Fawad Salam Khan, Muhammad Inam Abbasi, Muhammad Khurram, Mohd Norzali Haji Mohd, M. Danial Khan,

Breast cancer incidences have grown worldwide during the previous few years. The histological images obtained from a biopsy of breast tissues are regarded as being the highest accurate approach to determine whether any cells exhibit symptoms of cancer. The visible position of nuclei inside the image is achieved through the use of instance segmentation, nevertheless, this work involves nucleus segmentation and features classification of the predicted nucleus for the achievement of best accuracy. The extracted features map using the feature pyramid network has been modified using SOLO convolution with grasshopper optimization for multiclass classification. A breast cancer multi-classification technique based on a suggested deep learning algorithm was examined to achieve the accuracy of 99.2% using a huge database of ICIAR 2018, demonstrating the method’s efficacy in offering an important weapon for breast cancer multi-classification in medical setting. The segmentation accuracy achieved is 88.46%.

10.11591/ijece.v12i4.pp%p

IJECE

Early Access

Advancements in energy storage technologies for smart grid development

Pankaj Sharma, Surender Reddy Salkuti, Seong-Cheol Kim,

In the modern world, the consumption of oil, coal natural gas, and nuclear energy has been causing by a serious environmental problem and an ongoing energy crisis. The generation and consumption of renewable energy sources (RESs) such as solar and wind tidal, can resolve the problem but the nature of the RESs is fluctuating and intermitted. This evolution brings a lot of challenges in the management of electrical grids. The paper reviewed the advancements in energy storage technologies for the development of a smart grid (SG). More attention was paid to the classification of energy storage technologies based on the form of energy storage and based on the form of discharge duration. The evaluation criteria for the energy storage technologies have been carried out based on technological dimensions such as storage capacity, efficiency, response time, energy density, and power density, the economic dimension such as input cost and economic benefit; and the environmental dimension such as emission and stress on ecosystem, social demission such as job creation and social acceptance were also presented in this paper.

10.11591/ijece.v12i4.pp%p

IJECE

Early Access

The effect of gaussian filter and data preprocessing on the classification of punakawan puppet images with the CNN algorithm

Kusrini Kusrini, Muhammad Resa Arif Yudianto, Hanif Al Fatta,

Nowadays, many algorithms are introduced, and some researchers focused their research on the utilization of convolutional neural network (CNN). CNN algorithm is equipped with various learning architectures, enabling researchers to choose the most effective architecture for classification. However, this research suggested that to increase the accuracy of the classification, preprocessing mechanism is another significant factor to be considered too. This study utilized Gaussian filter for preprocessing mechanism and VGG16 for learning architecture. The Gaussian filter was combined with different preprocessing mechanism applied on the selected dataset, and the measurement of the accuracy as the result of the utilization of the VGG15 learning architecture was acquired. The study found that the utilization of using contrast limited adaptive histogram equalization (CLAHE) + red green blue (RGB) + Gaussian Filter and Thresholding images showed the highest accuracy, 98.75%. Furthermore, another significant finding is that the Gaussian Filter was able to increase the accuracy on RGB images, however the accuracy decreased for green channel images. Finally, the use of CLAHE for dataset preprocessing increased the accuracy dealing with the green channel images.

10.11591/ijece.v12i4.pp%p

IJECE

Early Access

Coronavirus disease situation analysis and prediction using machine learning: A study on Bangladeshi population

Al-Akhir Nayan, Boonserm Kijsirikul, Yuji Iwahori,

During a pandemic, early prognostication of patient infected rates can reduce the death by ensuring treatment facility and proper resource allocation. In recent months, the number of death and infected rates has increased more distinguished than before in Bangladesh. The country is struggling to provide moderate medical treatment to many patients. This study distinguishes machine learning models and creates a prediction system to anticipate the infected and death rate for the coming days. Equipping a dataset with data from March 1, 2020, to August 10, 2021, a multi-layer perceptron (MLP) model was trained. The data was managed from a trusted government website and concocted manually for training purposes. Several test cases determine the model's accuracy and prediction capability. The comparison between specific models assumes that the MLP model has more reliable prediction capability than the support vector regression (SVR) and linear regression model. The model presents a report about the risky situation and impending coronavirus disease (COVID-19) attack. According to the prediction produced by the model, Bangladesh may suffer another COVID-19 attack, where the number of infected cases can be between 929 to 2443 and death cases between 19 to 57.

10.11591/ijece.v12i4.pp%p

IJECE

Early Access

Principal coefficient encoding for subject-independent human activity analysis

Pang Ying Han, Sarmela Anak Perempuan Raja Sekaran, Ooi Shih Yin, Tan Teck Guang,

Tracking human physical activity using smartphones is an emerging trend in healthcare monitoring and healthy lifestyle management. Neural networks are broadly used to analyze the inertial data of activity recognition. Inspired by the autoencoder neural networks, we propose a layer-wise network, namely principal coefficient encoder model (PCEM). Unlike the vanilla neural networks which apply random weight initialization and back-propagation for parameter updating, an optimized weight initialization is implemented in PCEM via principal coefficient learning. This principal coefficient encoding allows rapid data learning with no back-propagation intervention and no gigantic hyperparameter tuning. In PCEM, the most principal coefficients of the training data are determined to be the network weights. Two hidden layers with principal coefficient encoding are stacked in PCEM for the sake of deep architecture design. The performance of PCEM is evaluated based on a subject-independent protocol where training and testing samples are from different users, with no overlapping subjects in between the training and testing sets. This subject-independent protocol can better assess the generalization of the model to new data. Experimental results exhibit that PCEM outperforms certain state-of-the-art machine learning and deep learning models, including convolutional neural network, and deep belief network. PCEM can achieve ~97% accuracy in subject-independent human activity analysis.

10.11591/ijece.v12i4.pp%p

IJECE

Early Access

Determining the pareto front of distributed generator and static VAR compensator units placement in distribution networks

Bahman Ahmadi, Ramazan Çağlar,

The integration of distributed generators (DG), which are based on renewable energy sources, energy storage systems, and static VAR (SVC) compensators, requires considering more challenging operational cases due to the variability of DG production contributed by different characteristics for different time sequences. The size, quantity, technology, and location of DG units have major effects on the system to benefit from the integration. All these aspects create a multi-objective scope; therefore, it is considered a multi-objective mixed-integer optimization problem. This paper presents an improved multi-objective salp swarm optimization algorithm (MOSSA) to obtain multiple Pareto efficient solutions for the optimal number, location, and capacity of DGs and the controlling strategy of SVC a radial distribution system. MOSSA is a bio-inspired optimizer based on swarm intelligence techniques and it is used in finding the optimal solution for a global optimization problem. Two sets of objective functions have been formulated minimizing DGs and SVC cost, voltage violation, energy losses, and system emission cost. The usefulness of the proposed MOSSA has been tested with the 33-bus and 141-bus radial distribution systems and the qualitative comparisons against two well-known algorithms, multiple objective evolutionary algorithms based on decomposition (MOEA/D), and multiple objective particle swarm optimization (MOPSO) algorithm.

10.11591/ijece.v12i4.pp%p

IJECE

Early Access

A review of multi-agent mobile robot systems applications

Ammar Abdul Ameer Rasheed, Mohammed Najm Abdullah, Ahmed Sabah Al-Araji,

A multi-agent robot system (MARS) is one of the most important topics nowadays. The basic task of this system is based on distributive and cooperative work among agents (robots). It combines two important systems; multi-agent system (MAS) and multi-robots system (MRS). MARS has been used in many applications such as navigation, path planning detection systems, negotiation protocol, and cooperative control. Despite the wide applicability, many challenges still need to be solved in this system such as the communication links among agents, obstacle detection, power consumption, and collision avoidance. In this paper, a survey of motivations, contributions, and limitations for the researchers in the MARS field is presented and illustrated. Therefore, this paper aims at introducing new study directions in the field of MARS.

10.11591/ijece.v12i4.pp%p

IJECE

Early Access

Scalable decision tree based on fuzzy partitioning and an incremental approach

Somayeh Lotfi, Mohammad Ghasemzadeh, Mehran Mohsenzadeh, Mitra Mirzarezaee,

Classification as a data mining materiel is the process of assigning entities to an already defined class by examining the features. The most significant feature of a decision tree as a classification method is its ability to data recursive partitioning. To choose the best attributes for partition, the value range of each continuous attribute should be divided into two or more intervals. Fuzzy partitioning can be used to reduce noise sensitivity and increase the stability of trees. Also, decision trees constructed with existing approaches, tend to be complex, and consequently are difficult to use in practical applications. In this article, a fuzzy decision tree has been introduced that tackles the problem of tree complexity and memory limitation by incrementally inserting data sets into the tree. Membership functions are generated automatically. Then Fuzzy Information Gain is used as a fast-splitting attribute selection criterion and the expansion of a leaf is done attending only with the instances stored in it. The efficiency of this algorithm is examined in terms of accuracy and tree complexity. The results show that the proposed algorithm by reducing the complexity of the tree can overcome the memory limitation and make a balance between accuracy and complexity.

10.11591/ijece.v12i4.pp%p

IJECE

Early Access

Smart offload chain: a proposed architecture for blockchain assisted fog offloading in smart city

Minal Patel, Bhavesh Gohil, Sanjay Chaudhary, Sanjay Garg,

Blockchain enables smart contract for secure data transfer by which fog offloading servers can have trustworthy access control to work with data execution. When cloud is used for handling requests from mobile users, the attacker may perform denial of service attack and the same is possible at fog nodes and the same can be handled with the help of blockchain technology. In this paper, smart city application is discussed ause case study for blockchain based fog computing architecture. We propose a novel offload chain architecture for blockchain-based offloading in internet of things (IoTs) networks where mobile devices can offload their data to fog servers for computation by an access control mechanism. The offload chain model using deep reinforcement learning (DRL) is proposed to improve the efficiency of blockchain based fog offloading amongst existing models. 

10.11591/ijece.v12i4.pp%p

IJECE

Early Access

Modeling and analysis of energy losses under transient conditions in induction motors

Ayman Al-Rawashdeh, Ali Dalabeeh, Ashraf Samarah, Abdallah Ershoud Alzyoud, Khalaf Alzyoud,

The present study is mainly concerned with solving the problems associated with energy losses resulting from starting transient conditions. In the present study, the possibilities of decreasing starting transient condition energy losses are investigated. Additionally, a comparison of the energy losses using different starting methods is also conducted. In this work, a complete description for deriving the equations used to calculate energy losses, mathematical analysis of the energy losses, the models of the different methods in this work were simulated using Simulink/MATLAB; and the results of energy losses and the dynamic characteristics are provided. Simulation results showed that the minimum starting energy losses were accomplished by soft starting method; in which the starting current could be reduced to the minimum value.

10.11591/ijece.v12i4.pp%p
More Articles ...

14147

Articles

45433

Subjects

44527

Authors

20030

Total Views

ipmuGoDigital Library

Copyright © 2021 IpmuGo Digital Library.

All Right Reserved

Support

Help Center

Privacy Policy

Terms of Service