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

31,456 Article Results

Learning face similarities for face verification using hybrid convolutional neural networks

10.11591/ijeecs.v16.i3.pp1333-1342
Fadhlan Hafizhelmi Kamaru Zaman , Juliana Johari , Ahmad Ihsan Mohd Yassin
Face verification focuses on the task of determining whether two face images belong to the same identity or not. For unrestricted faces in the wild, this is a very challenging task. Besides significant degradation due to images that have large variations in pose, illumination, expression, aging, and occlusions, it also suffers from large-scale ever-expanding data needed to perform one-to-many recognition task. In this paper, we propose a face verification method by learning face similarities using a Convolutional Neural Networks (ConvNet). Instead of extracting features from each face image separately, our ConvNet model jointly extracts relational visual features from two face images in comparison. We train four hybrid ConvNet models to learn how to distinguish similarities between the face pair of four different face portions and join them at top-layer classifier level. We use binary-class classifier at top-layer level to identify the similarity of face pairs which includes a conventional Multi-Layer Perceptron (MLP), Support Vector Machines (SVM), Native Bayes, and another ConvNet. There are 3 face pairing configurations discussed in this paper. Results from experiments using Labeled face in the Wild (LFW) and CelebA datasets indicate that our hybrid ConvNet increases the face verification accuracy by as much as 27% when compared to individual ConvNet approach. We also found that Lateral face pair configuration yields the best LFW test accuracy on a very strict test protocol without any face alignment using MLP as top-layer classifier at 87.89%, which on-par with the state-of-the-arts. We showed that our approach is more flexible in terms of inferencing the learned models on out-of-sample data by testing LFW and CelebA on either model.
Volume: 16
Issue: 3
Page: 1333-1342
Publish at: 2019-12-01

Validation of diabetes mellitus patient behavior questionnaire in primary health care service

10.11591/ijphs.v8i4.18348
Ginanjar Zukhruf Saputri , Akrom Akrom , Haafizah Dania , Okta Muthia S
This study aimed to develop and validation a questionnaire as measurement instrument for knowledge and adherence behavior of DM patients in primary health care. Cross sectional study design was conducted in diabetes mellitus patient. Inclusion criteria were patients in the age group 18-65 years, diagnosed with DM, receiving at least one oral antidiabetic medication. Questionnaire questions for behavioral item were developed based on Diabetes Mellitus management guidelines and references to previous studies. Evaluation and validation by expert was carried out on diabetes mellitus experts and clinical psychologists. The pilot study was conducted on 10 healthy patients and 10 patients with diabetes who enrolled inclusion criteria. Questionnaire validation test was conducted with 41 DM outpatient at PKU Muhammadiyah Hospital in Yogyakarta. Collecting data by interviewing patients based on questionnaire. Statistical analysis was performed using SPSS with Pearson correlation coefficients for validation test and Cronbach alpha coefficients for reliability test of the questionnaire. Adherence behavior questionnaire consists of 12 question items, which are divided into three domains: cognitive, affective, and psychomotor domains. Validation results showed 12 valid items where the pearson correlation value was>0.308 (n=41). Cronbach alpha as reliability test results showed 0.78. This result showed a questionnaire were valid and reliable in Diabetes Mellitus patients. This instrument would be use in primary health care for measuring adherence behavior of DM patients.
Volume: 8
Issue: 4
Page: 455-460
Publish at: 2019-12-01

A leakage current estimation based on thermal image of polymer insulator

10.11591/ijeecs.v16.i3.pp1096-1106
Darwison Darwison , Syukri Arief , Hairul Abral , Ariadi Hazmi , M. H. Ahmad , Eka Putra Waldi , Rudy Fernandez
Polymer insulators tend to fail because of the climatic and environmental conditions. The failure occurs when the surface of insulator is contaminated by sea salt or cement dust which lead to partial discharge (PD). Leakage currents will increase by PD that causes deterioration of insulation. To predict the insulation failures, an  adaptive neurofuzzy inference system (ANFIS) method using initial color detection processes are proposed to estimate the leakage currents based on the polymer insulator thermal images (infrared signature). In this study, the sodium chloride and kaolin are used as pollutants of the polymer insulator according to IEC 60507 standards. Then, the insulator is tested in the laboratory using AC high voltage applied at 18 kV where the temperature detection is controlled at 26° C and 70% RH (relative humidity). The percentage of colors (Red, Yellow, and Blue) from the thermal image is measured using the color detection method. Correspond to the color percentage, the ANFIS method predicts leakage currents from polymer insulators. Furthermore, this system interprets measured data from insulators that need to be categorized as Safe, Need Maintenance or Harmful. The final application of the system can be a non-contact tool to predict the polymer insulators used by technicians in the field.
Volume: 16
Issue: 3
Page: 1096-1106
Publish at: 2019-12-01

Evaluation of computer network security using attack undirected geography

10.11591/ijeecs.v16.i3.pp1508-1514
Chanintorn Jittawiriyanukoon
To secure a wealth of data traversing the computer network at your fingertips is compulsory. But when attack arises at various parts of the network it is difficult to protect, especially when each incident is investigated separately. Geography is a necessary construct in computer networks. The analytics of geography algorithms and metrics to curate insight from a security problem are a critical method of analysis for computer systems. A geography based representation is employed to highlight aspects (on a local and global level) of a security problem which are Eigenvalue, eccentricity, clustering coefficient and cliques. Network security model based on attack undirected geography (AUG) is familiarized. First, analysis based upon association rules is presented then the attack threshold value is set from AUG. The probability of an individual attack edge and associated network nodes are computed in order to quantify the security threat. The simulation is exploited to validate that results are effective.
Volume: 16
Issue: 3
Page: 1508-1514
Publish at: 2019-12-01

The best predictor of anxiety, stress, and depression among institutionalized elderly

10.11591/ijphs.v8i4.20359
Ni Putu Wulan Purnama Sari , Maria Manungkalit
Anxiety, stress, and depression are the three most common negative emotional constructs found in the elderly. Evidences available worldwide about how psychological problem could be resulted in mental disorder, and there is significant difference in the context of living in the nursing home and in community setting. This study aimed to determine the best predictor of anxiety, stress, and depression in elderly living in the nursing home, useful for future modification and intervention development. This cross-sectional study involved 145 elderly in a private nursing home in Surabaya, Indonesia. HARS, SPST-20, and GDS were used in data collection. Linear regression and one way ANOVA tests were used in data analysis (α<0.05). Results showed that mostly in old individuals, mild anxiety and stress, and undepressed state were found. Sensory problems and concentration difficulties were the best predictor of anxiety and stress respectively, which were accounted for 61.2% and 65.6% variances of anxiety and stress in nursing home residents respectively. Spirits, life energy, happiness, and feeling wonderful to be alive could not predict depression significantly. Feeling inferior to others is the best predictor of depression, which was accounted for 25.9% variance of depression in this population. Low self-esteem leads to depression in nursing home residents.
Volume: 8
Issue: 4
Page: 419-426
Publish at: 2019-12-01

Spiritual wellbeing in breast and cervical cancer survivors: differences in each stage of survivorship

10.11591/ijphs.v8i4.20311
Ni Putu Wulan Purnama Sari
Spiritual needs in cancer survivors are underappreciated compared to physical and psychological needs. This study aimed to: 1) compare and analyze the differences in spiritual wellbeing (SWB) between breast and cervical cancer survivors (BCS and CCS) generally, and between stages of survivorship specifically, and 2) determine the best predictor of SWB in both cases. This cross-sectional study involved 58 BCS and 47 CCS (n=105). Questionnaire of QOL-CS part IV was used in data collection. Various statistical tests were used in data analysis (α<0.05). SWB was significantly different between BCS and CCS (p=0.002), which influenced by significant differences in religious activity, spiritual activity, uncertainty, positive life changes, life goals, and hope (all p<α). In BCS, overall SWB was not significantly different between survivorship stages (p=0.179); but religious activity, life goals, and hope were significantly different (p=0.043, p=0.022, and p=0.036 respectively) which indicate that these three aspects change overtime along with the survivorship stages. While in CCS, SWB and all of its aspects were not significantly different between survivorship stages (all p>α) which indicate that SWB is stable/stagnant across the survival life span in CCS. Spiritual life changes and religious activity are the best predictors of SWB in both cases and were accounted for 70.3% (R2=0.703) and 69.7% (R2=0.697) variance of SWB in BCS and CCS respectively.
Volume: 8
Issue: 4
Page: 441-454
Publish at: 2019-12-01

Variable structure control for an isolated boost converter used in fuel cell applications

10.11591/ijece.v9i6.pp4493-4506
S. Vijaya Madhavi , G. Tulasi Ram Das
In recent years fuel cells have become prominent as an alternative source of energy to meet the society’s energy requirements. A control strategy derived from variable structure theory known as Sliding Mode Control (SMC) was proposed for an Isolated Boost topology which was mostly used in fuel cell systems. Converter operation and its detailed mathematical modelling are also presented. Then the converter with the control strategy suggested is simulated in MATLAB/SIMULINK and compared with other controllers. The results show that transient response of the converter is very fast and steady state error is reduced throughout the load change period with proposed control topology.
Volume: 9
Issue: 6
Page: 4493-4506
Publish at: 2019-12-01

Fuzzy n-s-homogeneity and fuzzy weak n-s-homogeneity

10.11591/ijece.v9i6.pp5395-5399
Samer Al Ghour , Almothana Azaizeh
Fuzzy n-s-homogeneity and fuzzy weak n-s-homogeneity are introduced in fuzzy bitopological spaces. Several relationships, characterizations and examples related to them are given.
Volume: 9
Issue: 6
Page: 5395-5399
Publish at: 2019-12-01

Developing the indonesian government enterprise architecture framework appropriate for Indonesian government agencies

10.11591/ijict.v8i3.pp152-161
Asbartanov Lase , Benny Ranti
This research was conducted to develop the Indonesian Government Enterprise Architecture (IGEA) framework which is suitable for Indonesian government agencies. Due to their complexity and expensive implementation cost, existing EA frameworks such as TOGAF and Zachman have so far not been the choice for building GEA by some countries including Australia and New Zealand. Those countries have built their own GEA namely Australia’s AGA and New Zealand’s GEA-NZ, respectively. Learning from this experience, the authors did a research to build Indonesia’s GEA or IGEA. This paper explains the research process which starts from mapping or comparing TOGAF, AGA, and GEA-NZ frameworks to get the underlying foundation for building GEA, analyzing framework artifacts, to building IGEA by adding specific Indonesian regulations and policies such as RPJMN and Nawacita. This IGEA framework is expected to become a reference for developing EA not only at institutional level but also the most important thing at national or cross institutional level, in order to increase the effectiveness of government IT spending.
Volume: 8
Issue: 3
Page: 152-161
Publish at: 2019-12-01

Estimation of object location probability for object detection using brightness feature only

10.11591/ijece.v9i6.pp5227-5234
Hyun Jun Park , Kwang Baek Kim
Most existing object detection methods use features such as color, shape, and contour. If there are no consistent features can be used, we need a new object detection method. Therefore, in this paper, we propose a new method for estimating the probability that an object can be located for object detection and generating an object location probability map using only brightness in a gray image. To evaluate the performance of the proposed method, we applied it to gallbladder detection. Experimental results showed 98.02% success rate for gallbladder detection in ultrasonogram. Therefore, the proposed method accurately estimates the object location probability and effectively detected gallbladder.
Volume: 9
Issue: 6
Page: 5227-5234
Publish at: 2019-12-01

Comparison by simulation of PEGASIS and IEEPB routing protocols

10.11591/ijeecs.v16.i3.pp1569-1576
Samah Alnajdi , Fuad Bajaber
As the applications of wireless sensor networks (WSNs) became widely used throughout the years the importance of advanced sensor networks techniques increased as well. One of the main techniques used in WSNs is hierarchical routing which mainly aims to reduce the consumption of sensor nodes energy by assigning different roles to the sensor nodes to create multi-layer scheme for data transmission. This paper embraces a simulation for two known hierarchical routing protocols: Power-Efficient Gathering in Sensor Information Systems (PEGASIS) protocol and an Improved Energy-Efficient PEGASIS-Based (IEEPB) protocol. Both protocols aim to reduce the transmission distance in order to save the nodes energy by performing chain-based clustering. For evaluation, we measured the residual energy and control overhead throughout the network operation time and the results showed major flaws in both protocols such as long link problem and poor leader selection method in PEGASIS. Moreover, high nodes density problem in IEEPB.
Volume: 16
Issue: 3
Page: 1569-1576
Publish at: 2019-12-01

Improve of contrast-distorted image quality assessment based on convolutional neural networks

10.11591/ijece.v9i6.pp5604-5614
Ismail Taha Ahmed , Chen Soong Der , Norziana Jamil , Mohamad Afendee Mohamed
Many image quality assessment algorithms (IQAs) have been developed during the past decade. However, most of them are designed for images distorted by compression, noise and blurring. There are very few IQAs designed specifically for Contrast Distorted Images (CDI), e.g. Reduced-reference Image Quality Metric for Contrast-changed images (RIQMC) and NR-IQA for Contrast-Distorted Images (NR-IQA-CDI). The existing NR-IQA-CDI relies on features designed by human or handcrafted features because considerable level of skill, domain expertise and efforts are required to design good handcrafted features. Recently, there is great advancement in machine learning with the introduction of deep learning through Convolutional Neural Networks (CNN) which enable machine to learn good features from raw image automatically without any human intervention. Therefore, it is tempting to explore the ways to transform the existing NR-IQA-CDI from using handcrafted features to machine-crafted features using deep learning, specifically Convolutional Neural Networks (CNN).The results show that NR-IQA-CDI based on non-pre-trained CNN (NR-IQA-CDI-NonPreCNN) significantly outperforms those which are based on handcrafted features. In addition to showing best performance, NR-IQA-CDI-NonPreCNN also enjoys the advantage of zero human intervention in designing feature, making it the most attractive solution for NR-IQA-CDI.
Volume: 9
Issue: 6
Page: 5604-5614
Publish at: 2019-12-01

An enhanced particle swarm optimization algorithm

10.11591/ijece.v9i6.pp4904-4907
Wameedh Riyadh Abdul-Adheem
In this paper, an enhanced stochastic optimization algorithm based on the basic Particle Swarm Optimization (PSO) algorithm is proposed. The basic PSO algorithm is built on the activities of the social feeding of some animals. Its parameters may influence the solution considerably. Moreover, it has a couple of weaknesses, for example, convergence speed and premature convergence. As a way out of the shortcomings of the basic PSO, several enhanced methods for updating the velocity such as Exponential Decay Inertia Weight (EDIW) are proposed in this work to construct an Enhanced PSO (EPSO) algorithm. The suggested algorithm is numerically simulated established on five benchmark functions with regards to the basic PSO approaches. The performance of the EPSO algorithm is analyzed and discussed based on the test results.
Volume: 9
Issue: 6
Page: 4904-4907
Publish at: 2019-12-01

Design and implementation of a Context-Aware Health Service Platform (CAHS)

10.11591/ijece.v9i6.pp4993-5005
Siham Belhadi , Rachid Merzougui
Computers are no match to humans in deducing situational information from their environment and in using it in their interactions. The advent of the context-aware applications seems to offer a way out to the computer that is not context-sensitive. The context aware applications can adapt their behaviors according to the perceived context or situation, without explicit user intervention, thereby providing human-centric services. To simplify the complexity of developing applications, context aware framework, which introduces context awareness into the environment where the applications are executed, is highlighted to provide a homogeneous interface involving generic context management and adaptation solutions. This papier has focused on the design of Context-Aware Health Services (CAHS) platform, which provide a health applications framework embedded on mobile devices. Our proposed platform is capabilities for context manager and adaptations according to context changes. It is designed to base on the SOA principles for achieving a flexible and dynamic architecture.
Volume: 9
Issue: 6
Page: 4993-5005
Publish at: 2019-12-01

GIS based probabilistic method in sinkhole susceptibility hazard zones

10.11591/ijeecs.v16.i3.pp1539-1546
Mohd Asri Hakim Mohd Rosdi , Ainon Nisa Othman , Zulkiflee Abd Latif , Zaharah Mohd Yusoff
In this era of globalization, natural phenomena often invade the human population. Natural phenomena such as sinkholes often occur in countries whose topology lies in active limestone areas. Malaysia is one of the countries with active limestone areas, especially in the Klang Valley and its surrounding areas. Since 1968, the increase in sinkhole cases in Malaysia has been reported frequently. This has caused many building infrastructures to be destroyed, loss of life and destruction of property. So, one of the steps to overcome this problem is to do an in-depth study of the sinkhole. Therefore, Sinkhole Hazard Model (SHM) has been created with a combination of GIS integration by using probability techniques. There are five criteria suitable for Malaysian topography namely Lithology (LT), Soil Types (ST), Landuse (LU), Groundwater Level Decline (GLD) and Proximity to Groundwater Wells (PGW). Based on probability calculations, GLD and LU have shown a high impact on sinkhole formation. A hazard zonation map has been produced where it has been classified into five parts namely none, low, medium, high and very high. The results were validated with previous inventory data comprising 33 data. Based on the results obtained, 36.37% and 39.39% of the sinkhole formation has fallen into high and very high areas respectively. Based on these final results, the integration between GIS and probability techniques is useful in natural phenomena such as sinkhole formation.
Volume: 16
Issue: 3
Page: 1539-1546
Publish at: 2019-12-01
1 2 3
...
2097 2098
Show 1327 of 2098

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