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

Anomaly event detection and localization of video clips using global and local outliers

10.11591/ijeecs.v24.i2.pp1063-1073
Sawsen Abdulhadi Mahmood , Azal Monshed Abid , Sadeq H. Lafta
The automatic detection of anomaly events in video sequence has become a critical issue and essential demand for the extensive deployment of computer vision systems such as video surveillance applications. An anomaly event in video can be denoted as outlier behavior within video frames which formulated by a deviation from the stable scene. In this paper, an anomaly event detection and localization method in video sequence is presented including multilevel strategy as temporal frames differences estimation, modelling of normal and abnormal behavior using regression model and finally density–based clustering to detect the outliers (abnormal event) at clips level. Hence, outlier score is obtained at the segment or clip level along video frames sequences. The proposed method seplits video frames into nonoverlapped clips using global outlier detection process. Afterward, at each clip, the local outliers are determined based on density of each clip. Extensive experiments were conducted upon two public video datasets which include dense and scattered outliers along video sequence. The experiments were performed on two common public datasets (Avenue) and University of California, San Diego (UCSD). The experimental results exhibited that the proposed method detects well outlier frames at clip level with lower computational complexity comparing to the state-of-the-art methods.
Volume: 24
Issue: 2
Page: 1063-1073
Publish at: 2021-11-01

Sidelobe level minimization for uniform circular smart antenna array using cultural algorithm

10.11591/ijeecs.v24.i2.pp930-936
Asma Issa Mohsin , Asaad S. Daghal , Adheed Hasan Sallomi
Cultural algorithm (CA) is a new evolutionary program inspired by sociology and archaeology theories that assisting formulating cultural evaluation. Its use to solve optimization problems. This paper analyzed the beamforming of a uniform circular antenna array (UCAA) via using the CA algorithm. The sidelobe level (SLL) is minimized by adjusting the appropriate weight for each element. In addition, the optimal beam pattern is achieved by using CA for UCAA, which means that the main beam is steering to the desired user, while the nulls represent the interference signals. The excitation amplitude is supposed to be constant while the elements are assumed isotropic. The circular array number elements and the interspacing distance between them are setting as optimization parameters. The simulation results show that the CA rationally reacts to the changing environments, and it is valuable for SLL reduction. A −25 dB of relative SLL is achieved under beam scanning (0º) and (15º), respectively.
Volume: 24
Issue: 2
Page: 930-936
Publish at: 2021-11-01

Electromagnetic nonlinear parametric study of the SynRM using FEM method

10.11591/ijeecs.v24.i2.pp637-648
Benessalah Djamel , Houassine Hamza , Nadir Kabache , Moussaoui Djeloul
The interest in synchronous reluctance machine (SynRM) does not stop increasing in recent decades; this is encouraged by their numerous advantages. This paper presents a nonlinear parametric study of the SynRM using finite element method (FEM) method. After a brief introduction and a description of the basic principles of SynRM an investigation and an evaluation of the effects of some influential parameters’ variables of the machine on the torque and magnetic losses is highlighted. The SynRM is created using ANSYS Maxwell software, using 2D FEM. The analyses are performed in the ANSYS Maxwell. The influence of the thickness of the air gap, the opening angle of the rotor, the width and the height of the stator tooth are listed and discussed. The obtained results reveals that the opening angle of the rotor and the air gap produces a large effect over the torque of the SynRM. In order to validate, the finite element model of the studied machine, experimental tests were carried out on designed machine such as the measurement of the synchronous inductance, the torque and the different losses. The experimental results are in agreement with those obtained by FEM.
Volume: 24
Issue: 2
Page: 637-648
Publish at: 2021-11-01

Magnetic sensitivity modeling of dual gate MOS transistor

10.11591/ijeecs.v24.i2.pp1238-1248
Mohamed Kessi , Arezki Benfdila
In this paper, the magnetic field effect on the carrier transport phenomenon in the double gate metal-oxide-semiconductor field-effect transistor (MOSFET) has been investigated. This is done by exploring the Lorentz force and the behavior of a semiconductor subjected to a constant magnetic field. The magnetic field modulates the electrons position and density as well as the potential distribution in the case of silicon tunnel tunneling field-effects (FETs). This modulation impacts the device electrical characteristics such as ON current (ION), subthreshold leakage current (IOF), threshold voltage (VT), magneto-transconductance (gmm) and output magneto-conductance (gmDS). In addition, a hall voltage (VH) is induced and modulated by the magnetic field. It has been observed that this voltage influences the effective applied gate voltage. It has been observed that the threshold voltage variations induced by the magnetic field is of paramount importance and affects the device switching properties both speed and power dissipation, noted that the threshold voltage VT and (Ion/Iof) ratio are reduced by 10-3V and 102 for a magnetic field of ±6 and ±5.5 Tesla, respectively. We have simulated the different behavior in the channel, mainly doping concentration, potential distribution, conduction and valence bands, total current density, total charge density, electric field, electron mobility, and electron velocity.
Volume: 24
Issue: 2
Page: 1238-1248
Publish at: 2021-11-01

Application of the Jaya algorithm to solve the optimal reliability allocation for reduction oxygen supply system of a spacecraft

10.11591/ijeecs.v24.i2.pp1202-1211
Saad Abbas Abed , Mohammad Aljanabi , Noor Hayder Abdul Ameer , Mohd Arfian Ismail , Shahreen Kasim , Rohayanti Hassan , Tole Sutikno
In this paper the reliability of reduction oxygen supply system (ROSS) of a spacecraft which was calculated as a complex system using minimal cut method. The reliability of each component of system was calculated as well as the reliability importance of the system. The cost of each component of the system was possible approaches of the allocation values of reliability based the minimization of the overall cost in this system. The advantage of this algorithm can be used to allocate the optimization of reliability for simple or complex system. This optimization is achieved using the Jaya algorithm. The proposed technique is based on the notion that a conclusion reached on a particular problem should pass near the best results and avoid the worst outcomes. The original findings of this paper are: i) the system used in this paper is a spacecraft’s reduced oxygen supply system with the logarithmic cost function; and ii) the results obtained were by using the Jaya algorithm to solve specific system reliability optimization problems.
Volume: 24
Issue: 2
Page: 1202-1211
Publish at: 2021-11-01

An efficient data masking method for encrypted 3D mesh model

10.11591/ijeecs.v24.i2.pp957-964
Manikamma Malipatil , D. C. Shubhangi
The industrial 3D mesh model (3DMM) plays a significant part in engineering and computer aided designing field. Thus, protecting copyright of 3DMM is one of the major research problems that require significant attention. Further, the industries started outsourcing its 3DMM to cloud computing (CC) environment. For preserving privacy, the 3DMM are encrypted and stored on cloud computing environment. Thus, building efficient data masking of encrypted 3DMM is considered to be efficient solution for masking information of 3DMM. First, using the secret key, the original 3DMM is encrypted. Second without procuring any prior information of original 3DMM it is conceivable mask information on encrypted 3D mesh models. Third, the original 3DMM are reconstructed by extracting masked information. The existing masking methods are not efficient in providing high information masking capacity in reversible manner and are not robust. For overcoming research issues, this work models an efficient data masking (EDM) method that is reversible nature. Experiment outcome shows the EDM for 3DMM attain better performance in terms of peak signal-to-noise ratio (PSNR) and root mean squared error (RMSE) over existing data masking methods. Thus, the EDM model brings good tradeoffs between achieving high data masking capacity with good reconstruction quality of 3DMM.
Volume: 24
Issue: 2
Page: 957-964
Publish at: 2021-11-01

Automation of the stone materials dosing process, controlled by variable frequency drives

10.11591/ijeecs.v24.i2.pp794-802
Guillermo Morales-Romero , Nicéforo Trinidad-Loli , Adrián Quispe-Andía , Beatriz Caycho-Salas , Shirley Quispe-Guía , Carlos Palacios-Huaraca , Omar Chamorro-Atalaya
The objective of this article is to determine to what extent the automation of the stone materials dosing process, controlled by sequential drive of frequency variators, contributes to improving the productivity of a company dedicated to the production of asphalt in Peru for which, initially, the characteristics of the procedure that will lead to achieving the automation will be described. The results will then be displayed with respect to the indicators used to compare productivity before and after automation. The automation will be done by means of the logo 230RE controller, which will be connected to three frequency inverters, the programming development will be through the logo soft comford V8 software, for the sequential actuation, timers with connection delay will be used. Applying the automation, it is possible to improve the annual efficiency by an average of 58.30%, this is reflected in the monthly decrease in production time by 13.92%, in turn increasing the amount of stone material produced by an average of 43.77%. Likewise, it is possible to significantly reduce the production loss capacity by an annual average of 93.99%.
Volume: 24
Issue: 2
Page: 794-802
Publish at: 2021-11-01

Modern tools and current trends in web-development

10.11591/ijeecs.v24.i2.pp978-985
Debani Prasad Mishra , Kshirod Kumar Rout , Surender Reddy Salkuti
In this paper, a social media platform like LinkedIn and Facebook is made using MongoDB as a database. This paper aims to touch all the modern tools required to make an efficient web app, keeping in mind both the customer satisfaction and the ease for the developers to make their web designs, front-end and back-end. In this application, a user could make an account, add or delete details of their profile, education, and experience fields. The users could post, also comment and even like a post of other users. A monolithic architectural approach is used for simplicity in maintaining the database. Postman application programming interface (API) was used to check the working of the back-end. Git, Github, and Heroku were used to deploy the website. Node package manager (NPM) packages like bcrypt and validator are used to encrypt passwords and to validate a user during login. Media queries are used in cascading style sheets (CSS) to achieve a responsive design. Therefore, the users could view the website through a mobile phone, i-pad and also a personal computer (PC), maintaining the readability and design across all these devices.
Volume: 24
Issue: 2
Page: 978-985
Publish at: 2021-11-01

IPOC: an efficient approach for dynamic association rule generation using incremental data with updating supports

10.11591/ijeecs.v24.i2.pp1084-1090
P. Naresh , R. Suguna
According to recent statistics, there was drastic growth in online business sector where more number of customers intends to purchase items. Due to these retailers accumulates huge volumes of data from day to day operations and engrossed in analyzing the data to watch the behavior of customers at items which strengthen the business promotions and catalog management. It reveals the customer interestingness and frequent items from large data. To carry out this there was known algorithms present which deals with static and dynamic data. Some of them are lag time and memory consuming and involves unnecessary process. This paper intents to implement an efficient incremental pre ordered coded tree (IPOC) generation for data updates and applies frequent item set generation algorithm on the tree. While incremental generation of tree, new data items will link to previous nodes in tree by increasing its support count. This removes the lagging issues in existing algorithms and does not need to mine from scratch and also reduces the time, memory consumption by the use of nodeset data structure. The results of proposed method was observed and analyzed with existing methods. The anticipated method shows improved results by means of generated items, time and memory.
Volume: 24
Issue: 2
Page: 1084-1090
Publish at: 2021-11-01

Experimental study of through the wall imaging for the detection of vital life signs using SFWR

10.11591/ijeecs.v24.i2.pp825-830
Pardhu Thottempudi , Vijay Kumar
Now a day’s defence applications associated to novel, army and military war fields are required wall imaging discrimination. As of now many wallimaging techniques are designed but didn’t identify the vital signs behind walls with accurate working. Therefore, a novel advance wall image tracking method is required identification of human target. An experimental study on through the wallimaging (TWI) to detect the life signs using sweep frequency continuous wave radar (SFCWR) is explained in this paper. The proposed system consists of agilent vector network analyzer (VNA) (Agilent E5071B ENA), horn antenna and a computer. The information of heart beat and the breathing can be a shift identification routine was used to collect information from the back scattering electric current. The outcomes of the procedure give the information of heart beat and breathing signs of real human being.
Volume: 24
Issue: 2
Page: 825-830
Publish at: 2021-11-01

A novel hybrid face recognition framework based on a low-resolution camera for biometric applications

10.11591/ijeecs.v24.i2.pp853-863
Vijaya Kumar H. R. , M. Mathivanan
In research work, human face recognition is an essential biometric symbol persistently continued so far due to its different levels of applications in society. Since the appearance of the human faces can have many variations due to issues like the effect of illumination, expression and face pose. These differences are correlated with one another, which results in a helpless ability to recognize a particular person's face. The motivation behind our work in this paper is to give a new framework for face recognition based on frequency analysis that contributes to solving the distinguishing proof issues with enormous varieties of boundaries like the effect of illumination, expression, and face pose. Here three algorithms combined for provable results: i) Difference of Gaussian filtered discrete wavelet transform (DDWT) for feature extraction; ii) Log Gabor (LG) filter for feature extraction; and iv) Multiclass support vector machine classifier, where feature coefficients of DDWT and LG filter are fused for classification and parameters evaluation. The evaluation of our experiment is carried out on a large database consisting of 15 persons of each 200-face image which are captured using a 5-megapixel low-resolution web camera and yielding satisfactory results on various parameters compared to existing methods.
Volume: 24
Issue: 2
Page: 853-863
Publish at: 2021-11-01

Dropout, a basic and effective regularization method for a deep learning model: a case study

10.11591/ijeecs.v24.i2.pp1009-1016
Brahim Jabir , Noureddine Falih
Deep learning is based on a network of artificial neurons inspired by the human brain. This network is made up of tens or even hundreds of "layers" of neurons. The fields of application of deep learning are indeed multiple; Agriculture is one of those fields in which deep learning is used in various agricultural problems (disease detection, pest detection, and weed identification). A major problem with deep learning is how to create a model that works well, not only on the learning set but also on the validation set. Many approaches used in neural networks are explicitly designed to reduce overfit, possibly at the expense of increasing validation accuracy and training accuracy. In this paper, a basic technique (dropout) is proposed to minimize overfit, we integrated it into a convolutional neural network model to classify weed species and see how it impacts performance, a complementary solution (exponential linear units) are proposed to optimize the obtained results. The results showed that these proposed solutions are practical and highly accurate, enabling us to adopt them in deep learning models.
Volume: 24
Issue: 2
Page: 1009-1016
Publish at: 2021-11-01

Development of a new rain attenuation model for tropical location

10.11591/ijeecs.v24.i2.pp937-948
Joseph Mom , Silas Soo Tyokighir , Gabriel Igwue
This study proposes a new rain attenuation prediction model (RAM) based on the rain cell concept for tropical locations. The new model addresses the research gap in the international telecommunications union (ITU) model. Results obtained show that the proposed RAM predicted the possibility of signal across seven (7) out of thirteen (13) stations monitored. The predicted attenuation values were 18.3427 dB, 18.8106 dB, 18.3921 dB, 13.8062 dB, 20.8803 dB, 9.4519 dB, and 19.6018 dB for Jalingo, Jos, Makurdi, Mubi, Otukpo, Sokoto, and Abuja respectively. However, the RAM predicted outage across six stations with predicted attenuation values of 31.7040 dB, 26.8302 dB, 28.6635 dB, 29.6562 dB, 28.8827 dB, and 30.0614 dB for Akwa-Ibom, Benin, Donga, Port-Harcourt, Owerri, and Aba respectively. The proposed RAM hence suggests an additional Ku-band spot beam power of at least 331.97 watts for Nigeria's Nigerian communication satellite-1 (NIGCOMSAT-1R) Ku-band transponder to overcome the predicted attenuation across the six stations which recorded signal outage. The results from this study can be used by network engineers for the implementation of fade mitigation techniques (FMTs) such as site diversity and power control to aid telecommunication networks anticipate changes and allocate resources accordingly.
Volume: 24
Issue: 2
Page: 937-948
Publish at: 2021-11-01

E-learning virtual meeting applications: A comparative study from a cybersecurity perspective

10.11591/ijeecs.v24.i2.pp1121-1129
Nader Abdel Karim , Ahmed Hussain Ali
During the coronavirus disease 2019 (COVID-19) pandemic outbreak, the lockdown of all activities including schools and universities became a normal habit, forcing educational institutes to find new ways to ensure the continuity of the learning process. E-learning is considered the best choice at this stage whereas using video conferencing or virtual meeting applications (VM) apps is the most common solution. In this research, security issues and possible cyber-attacks that may occur due to the use of the most popular VM apps used by educational institutes (i.e., Zoom, Microsoft Teams, and Google meet) are discussed. Moreover, the security features of these applications are briefly explained. Furthermore, a comprehensive comparison from a cybersecurity perspective between VM apps was made. The results show that Google Meet was the most secure against cyber-attacks, followed by the Microsoft Teams and finally the Zoom app.
Volume: 24
Issue: 2
Page: 1121-1129
Publish at: 2021-11-01

A simple, effective distance and density based outlier detection algorithm

10.11591/ijeecs.v24.i2.pp1141-1148
Sajidha S. A. , Udai Agarwal , Pruthviraj R. P. , Sparsh Agarwal , Nisha V. M. , Amit Kumar Tyagi
Outliers are eccentric data points with anomalous nature. Clustering with outliers has received a lot of attention in the data processing community. But, they inordinately affect the quality of the results obtained in case of popular clustering algorithms during the process of finding an optimal solution. In this work, we propose a novel method to classify the data points with grouping characteristics as either an outlier or not. We use both distance and density of a particular data point with respect to the rest of the data points for this process. Distances are used to find the points at the extremities while the densities are used to identify the data points at the sparsest spaces. Further, every data model has to take into account the aspect of generalization in order to work robustly even in out of the box situations. Hence, our approach provides a generalization aspect to the model. The accuracy of the proposed work is measured using area under curve (AUC) was found the highest for cardioto data set -AUC value-0.90 and second highest AUC value was obtained for Spambase data set -0.52 and several other datasets are used to demonstrate the usage of the model proposed.
Volume: 24
Issue: 2
Page: 1141-1148
Publish at: 2021-11-01
1 2 3
...
1995 1996
Show 895 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