Articles
9,174 Documents
A fast and non-trainable facial recognition system for schools
Kazeem Oyebode;
Kingsley Chiwuike Ukaoha
Indonesian Journal of Electrical Engineering and Computer Science Vol 25, No 2: February 2022
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v25.i2.pp989-994
Deep learning models have been at the forefront of facial recognition because they deliver improved classification accuracy over traditional ones. Regardless, deep learning models require an extensive dataset for training. To significantly cut down on its training time and dataset volume, pretrained models, have been used although, they are still required to undergo the usual training process for custom facial recognition tasks. This research focuses on an improved facial recognition system that lacks the training and retraining requirements. The system uses an existing deep learning feature extraction model. First, a user stands before a camera-enabled system. After that, the user supplies a unique identification number to fetch a corresponding face image from the database. This process generates two face feature vectors. One from the camera and that retrieved from the database. The cosine distance function determines the similarity value of these vectors. When the cosine distance value falls below a set threshold, the face is recognized and access granted. If the cosine distance of the two vectors gives a value above this threshold, access is denied. The proposed model performs satisfactorily on publicly available datasets.
Blind image watermarking scheme based on lowest energy contourlet transform coefficient and modified arnold cat/ikeda maps
Jinan N. Shehab;
Hussein A. Abdulkadhim;
Yousif Allbadi
Indonesian Journal of Electrical Engineering and Computer Science Vol 21, No 1: January 2021
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v21.i1.pp196-207
The widespread of global internet has led to the need for developing new methods of protecting multimedia information from exploitation, alteration or forgery, illegal distribution, and manipulation. An attacker is quickly and illegally distributing or changing multimedia information by using various means of computer technology. For detecting this manipulation, this paper suggests blind watermark image inside a host image for observing in the receiver. If the watermark image was retrieved, then the host image was not attacked or manipulated. While if not retrieved, in this case, the image was attacked. The proposed method is depending on a decomposition of the host image using lowest energy sub-bands of Contourlet transform (4-levels), with scrambling by Ikeda map of the watermark image, and selecting new positions by modified Arnold Cat map. This will produce more security and safety, as well as provide more difficulty or prevent hacking. The obtained results confirm the robustness against attacks and more effectiveness of the presented scheme compared with the other similar works. Also, using lowest energy sub-bands will expand area of embedding and this part will be considered in the future works with the color images.
Investigation of energy efficiency of two-way relay-assisted multi-band machine-to-machine communications
Hoang Thien Van;
Vo Tien Anh;
Danh Hong L.;
Chi Duong Thi Kim;
Hoang-Sy Nguyen
Indonesian Journal of Electrical Engineering and Computer Science Vol 23, No 2: August 2021
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v23.i2.pp863-870
In this paper, we improve the uplink energy efficiency (EE) of the multi-band machine-to-machine (M2M) communications underlaying cellular networks. In particular, based on the theory of stochastic geometry, we derive the closed-form expressions of the outage probability (OP), and the average energy efficiency of cellular and Machine-to-Machine users in two-way cooperative relaying networks with three-time-slot setting. We ensure the quality of service (QoS) by considering the OP and the average energy efficiency of all links. It is concluded that the three-time-slot relay-aided Machine-to-Machine communication can offer considerably high QoS and low transmission power for fairly distant machine-to-machine networks.
Reliability-based routing metric for UAVs networks
Musaab Mohammed Jasim;
Hayder Khaleel AL-Qaysi;
Yousif Allbadi
Indonesian Journal of Electrical Engineering and Computer Science Vol 21, No 3: March 2021
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v21.i3.pp1771-1783
As a result of technological advances in robotic systems, electronic sensors, and communication techniques, the production of unmanned aerial vehicle (UAV) systems has become possible. Their easy installation and flexibility led these UAV systems to be used widely in both military and civilian applications. Note that the capability of one UAV is however limited. Nowadays, a multi-UAV system is of special interest due to the ability of its associate UAV members either to coordinate simultaneous coverage of large areas or to cooperate to achieve common goals/targets. This kind of cooperation/coordination requires a reliable communication network with a proper network model to ensure the exchange of both control and data packets among UAVs. Such network models should provide all-time connectivity to avoid dangerous failures or unintended consequences. Thus, the multi-UAV system relies on communication to operate. Flying ad hoc network (FANET) is moreover considered as a sophisticated type of wireless ad hoc network among UAVs which solved the communication problems into other network models. Along with the FANET’s unique features, challenges and open issues are also discussed especially in the routing protocols approach. We will try to present the expected transmission account metric with a new algorithm for reliability. In addition to this new algorithm mechanism, the metric takes into account the relative speed between UAVs, and thus the increase of the fluctuations in links between UAVs has been detected. Accordingly, the results show that the function of the AODV routing protocol with this metric becomes effective in high mobility environments.
Improving model predictive control's optimization for urban traffic
Khelafa, Ilyas;
Baghdad, Abdenaceur;
El Hachimi, Mohamed
Indonesian Journal of Electrical Engineering and Computer Science Vol 25, No 3: March 2022
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v25.i3.pp1367-1374
When it comes to decreasing traffic congestion and enhancing mobility, traffic forecasting is critical. However, due to the complicated spatio-temporal dynamics of urban transportation networks, which are difficult to describe, this task is tough. Using a model predictive controller (MPC) provides the control of a traffic network's architecture as well as errors in its operations. Based on a real-time simulation, a novel, accurate prediction controller for urban traffic was presented in this study to estimate the number of cars at junctions and their waiting duration. Different optimization approaches were employed and evaluated to improve the MPC's performance. Simulation results demonstrated that the fmincon was very robust and could effectively reduce the number of vehicles in the link, in comparison with other algorithms This study also includes an in-depth analysis of the characteristics of various prediction horizon sets in an MPC. By increasing the prediction horizon, the amplitude of fluctuation became more important, but when Np=4, the fluctuations reduced.
Output voltage control of a PMSG with the DPC-SVM technique and high-order sliding mode
Mohammed Moumna;
Rachid Taleb;
Zinelaabidine Boudjema
Indonesian Journal of Electrical Engineering and Computer Science Vol 23, No 2: August 2021
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v23.i2.pp772-781
This paper aims to study the control of the output voltage of a wind turbine (WT) which is composed of a permanent magnet synchronous generator (PMSG) connected to an inverter/rectifier. The first tested control on PMSG is based on the classical direct power control (CDPC); this technique uses the active and reactive power as a control variable. Then, to improve the quality of energy and evaluate the performance of the system, we proposed a high-order sliding mode (HOSM) with space vector modulation (SVM) to controlthe output voltage. As a result, the proposed approach presents attractive features such as the chattering-free behavior of the sliding mode. This system was designed for a wind power conversion application in the case of an isolated site. The computer simulations were provided to verify the validity of the proposed control algorithm using the MATLAB/Simulink software.
Multi-scale 3D-convolutional neural network for hyperspectral image classification
Murali Kanthi;
Thogarcheti Hitendra Sarma;
Chigarapalle Shoba Bindu
Indonesian Journal of Electrical Engineering and Computer Science Vol 25, No 1: January 2022
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v25.i1.pp307-316
Deep Learning methods are state-of-the-art approaches for pixel-based hyperspectral images (HSI) classification. High classification accuracy has been achieved by extracting deep features from both spatial-spectral channels. However, the efficiency of such spatial-spectral approaches depends on the spatial dimension of each patch and there is no theoretically valid approach to find the optimum spatial dimension to be considered. It is more valid to extract spatial features by considering varying neighborhood scales in spatial dimensions. In this regard, this article proposes a deep convolutional neural network (CNN) model wherein three different multi-scale spatial-spectral patches are used to extract the features in both the spatial and spectral channels. In order to extract these potential features, the proposed deep learning architecture takes three patches various scales in spatial dimension. 3D convolution is performed on each selected patch and the process runs through entire image. The proposed is named as multi-scale three-dimensional convolutional neural network (MS-3DCNN). The efficiency of the proposed model is being verified through the experimental studies on three publicly available benchmark datasets including Pavia University, Indian Pines, and Salinas. It is empirically proved that the classification accuracy of the proposed model is improved when compared with the remaining state-of-the-art methods.
Show off the efficiency of dai-liao method in merging technology for monotonous non-linear problems
Rana Z. Al-Kawaz;
Abbas Y. Al-Bayati
Indonesian Journal of Electrical Engineering and Computer Science Vol 21, No 1: January 2021
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v21.i1.pp505-515
In this article, we give a new modification for the Dai-Liao method to solve monotonous nonlinear problems. In our modification, we relied on two important procedures, one of them was the projection method and the second was the method of damping the quasi-Newton condition. The new approach of derivation yields two new parameters for the conjugated gradient direction which, through some conditions, we have demonstrated the sufficient descent property for them. Under some necessary conditions, the new approach achieved global convergence property. Numerical results show how efficient the new approach is when compared with basic similar classic methods.
Customer’s spontaneous facial expression recognition
Golam Morshed;
Hamimah Ujir;
Irwandi Hipiny
Indonesian Journal of Electrical Engineering and Computer Science Vol 22, No 3: June 2021
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v22.i3.pp1436-1445
In the field of consumer science, customer facial expression is often categorized either as negative or positive. Customer who portrays negative emotion to a specific product mostly means they reject the product while a customer with positive emotion is more likely to purchase the product. To observe customer emotion, many researchers have studied different perspectives and methodologies to obtain high accuracy results. Conventional neural network (CNN) is used to recognize customer spontaneous facial expressions. This paper aims to recognize customer spontaneous expressions while the customer observed certain products. We have developed a customer service system using a CNN that is trained to detect three types of facial expression, i.e. happy, sad, and neutral. Facial features are extracted together with its histogram of gradient and sliding window. The results are then compared with the existing works and it shows an achievement of 82.9% success rate on average.
Differential equations of motion of a material point in the perpendicular plane to the plane of the gravitating disk
Zhenisgul Rakhmetullina;
Indira Uvaliyeva;
Farida Amenova
Indonesian Journal of Electrical Engineering and Computer Science Vol 24, No 3: December 2021
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v24.i3.pp1307-1314
This paper presents an analytical solution of the differential equations of motion of a material point in the plane perpendicular to the plane of the gravitating disk. The differential equations of the problem under study and the applied Gilden's method are described in the works of A. Poincaré. Differential equations refer to nonlinear equations. The analysis of methods for solving nonlinear differential equations was carried out. The methodology of applying the Gilden method to the solution of the differential equations under consideration can be applied in studies of the problem of the motion of celestial bodies in the “disk-material point” system in perpendicular planes. To identify the various properties of the gravitating disk, an analytical review of the state of the problem of the motion of a material point in the field of a gravitating disk is carried out. Summing up the presented review on the problem under study, a conclusion is made. The substantive formulation of the problem is described, which is formulated as follows: the study of the influence of disk-shaped bodies on the motion of a material point and methods for their solution.