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

29,922 Article Results

Intelligent cluster connectionist recommender system using implicit graph friendship algorithm for social networks

10.11591/ijai.v9.i3.pp497-506
Arnold Adimabua Ojugo , Debby Oghenevwede Otakore
Implicit clusters are formed as a result of the many interactions between users and their contacts. Online social platforms today provide special link-types that allows effective communication. Thus, many users can hardly categorize their contacts into groups such as “family”, “friends” etc. However, such contact clusters are easily represented via implicit graphs. This has arisen the need to analyze users’ implicit social graph and enable the automatic add/delete of contacts from/to a group via a suggestion algorithm – making the group creation process dynamic (instead of static, where users are manually added or removed). The study implements the friend suggest algorithm, which analyzes a user’s implicit social graph to create custom contact group using an interaction-based metric to estimate a user’s affinity to his contacts and groups. The algorithm starts with a small seed set of contacts – already categorized by a user as friends/groups; And, then suggest other contacts to be added to a group. The result inherent demonstrates the importance of both the implicit group relationships and the interaction-based affinity in suggesting friends.
Volume: 9
Issue: 3
Page: 497-506
Publish at: 2020-09-01

Parallel processing using big data and machine learning techniques for intrusion detection

10.11591/ijai.v9.i3.pp553-560
Alaeddine Boukhalfa , Nabil Hmina , Habiba Chaoni
Currently, information technology is used in all the life domains, multiple devices produce data and transfer them across the network, these transfers are not always secured, they can contain new menaces invisible by the current security devices. Moreover, the large amount and variety of the exchanged data cause difficulties related to the detection time. To solve these issues, we suggest in this paper, a new approach based on storing the large amount and variety of network traffic data employing Big Data techniques, and analyzing these data with Machine Learning algorithms, in a distributed and parallel way, in order to detect new hidden intrusions with less processing time. According to the results of the experiments, the detection accuracy of the Machine Learning methods reaches 99.9 %, and their processing time has been reduced considerably by applying them in a parallel and distributed way, which proves that our proposed model is effective for the detection of new intrusions.
Volume: 9
Issue: 3
Page: 553-560
Publish at: 2020-09-01

Improvement of cluster-based WSN protocol using fuzzy logic

10.11591/ijeecs.v19.i3.pp1540-1547
Jong-Yong Lee , Daesung Lee
A wireless sensor network is a collection of wireless nodes with sensor devices that can collect data from the real world. This is because sensor nodes usually use limited-powered batteries. Therefore, if the battery on the sensor node is exhausted, the node will no longer be available. If the battery on some nodes is discharged, the sensor network will not work properly. To maintain sensor network system, there are many wireless sensor network protocols to increase energy efficiency of nodes. One of the energy-efficient methods is cluster-based protocols. These protocols divide the sensor fields into clusters and send and receive data between nodes. Thus, depending on how the cluster is constructed, the network's lifetime may be reduced or increased. Cluster-based protocols cannot always be optimal cluster configurations. These problems have been improved using fuzzy logic. In general, fuzzy logic is used to elect cluster heads based on node residual energy, node concentration and node centrality. However, it is possible that nodes close to each other at a high density area are elected as cluster heads. In this paper, we propose a method to consider the number of adjacent cluster heads instead of Node Concentration to improve the problem.
Volume: 19
Issue: 3
Page: 1540-1547
Publish at: 2020-09-01

Illuminance levels based on different sky conditions by considering daylight harvesting

10.11591/ijeecs.v19.i3.pp1219-1225
Nik Sahidah Nik Ahmad , N. H. Radzi , Mohd Noor Abdullah
Daylight harvesting systems (DHS) offer the most effective and significant to reduce energy consumption. In the lighting system, there are various problems which include waste of energy consumption, inappropriate lighting and increasing greenhouse effect. Therefore, the waste of energy consumption should be reduced by controlling the dimming levels of artificial lighting according to the standard thus reducing the greenhouse effect. Hence, this paper considered the daylight adaptive for the lighting system to determine the dimming level and illuminance level for the office room. The simulation has been carried out using DIALux simulation lighting software to simulate the average daylight and average illuminance level with different conditions sky, which is clear, average, and overcast sky. Based on the result, the illuminance level has complied with the European Standard EN12464-1. Furthermore, the presence of daylight and weather conditions plays an essential role in the lighting system. The illuminance and dimming levels are different depending on the time and type of sky condition at that time. Therefore, the daylight adaptive in the lighting system can reduce the use of artificial light in the room.
Volume: 19
Issue: 3
Page: 1219-1225
Publish at: 2020-09-01

Age-based facial recognition using convoluted neural network deep learning algorithm

10.11591/ijai.v9.i3.pp424-428
Julius Yong Wu Jien , Aslina Baharum , Shaliza Hayati A. Wahab , Nordin Saad , Muhammad Omar , Noorsidi Aizuddin Mat Noor
Face recognition is the use of biometric innovations that can see or validate a person by seeing and investigating designs depending on the shape of the individual. Face recognition is used largely for the purpose of well-being, despite the fact that passion for different areas of use is growing. Overall, face recognition innovations are worth considering because they have the potential for broad legal jurisdiction and different business applications. It is widely used in many spaces. How it works is a product of facial recognition processing facial geometry. The hole between the ear and the good way from the front to the jaw are the main variables. This code distinguishes the highlight of the face that is important for your facial separation and creates your facial expression. Therefore, this study gives an overview of age detection using a different combination of machine learning and image processing methods on the image dataset.
Volume: 9
Issue: 3
Page: 424-428
Publish at: 2020-09-01

Automatic segmentation of ceramic materials with relaxed possibilistic C-Means clustering for defect detection

10.11591/ijeecs.v19.i3.pp1505-1511
Kwang Baek Kim , Doo Heon Song , Hyun Jun Park
Auromatic inspection system is necessary for reliable quality control if ceramic materials to avoid operator subjectivity and fatigue in visual inspection. Automatic segmentation from material’s image is then the most important process to develop such an inspection system. In this paper, we propose a Possibilistic C-Means pixel clustering algorithm with fuzzy stretching to form the defect object in segmentation. In experiment using 50 images containing a certain amount of defects, the proposed method was successful in 49 cases or 98% of opportunities. That performance is roughly twice better than that of standard K-means clustering in defect object formation Auromatic inspection system is necessary for reliable quality control if ceramic materials to avoid operator subjectivity and fatigue in visual inspection. Automatic segmentation from material’s image is then the most important process to develop such an inspection system. In this paper, we propose a Possibilistic C-Means pixel clustering algorithm with fuzzy stretching to form the defect object in segmentation. In experiment using 50 images containing a certain amount of defects, the proposed method was successful in 49 cases or 98% of opportunities. That performance is roughly twice better than that of standard K-means clustering in defect object formation.
Volume: 19
Issue: 3
Page: 1505-1511
Publish at: 2020-09-01

Implementation of DSSS system of image using MATLAB

10.11591/ijeecs.v19.i3.pp1358-1366
Samir Jasim Mohammed , Kadhim Hassan Kaittan
In direct sequence spread spectrum systems, pseudo sequence random (PN) are used to spreading data bits. There are various type of PN sequences are available with good correlation properties, on mostly are generating pn by linear feedback shift register (LFSR). Will examine in this paper we describe spreading binary random and spreading the image As well as studying probability bit error rate of DSSS system with change of the channel (Add white Gaussian noise channel, Rayleigh fading channel, Rician fading channel). Our study will be performed using MATLAB. Terms of completed my articles in building system developed to security transmitter and receiver the information of theft against communication digital system talk as well as the increase of data rate information. Was this design a way process of his used in applications military and have a major role also in the most applications requiring protect high for many information binary data and image. So that the system designed as fits practice and prevent the overlap the outside after it has become send signals in communication system exhibition penetration and Intentional attacks or other breaches.
Volume: 19
Issue: 3
Page: 1358-1366
Publish at: 2020-09-01

Quality and texture analysis of biometric images compressed with second-generation wavelet transforms and SPIHT-Z encoder

10.11591/ijeecs.v19.i3.pp1325-1339
Ahmed Bouida , Mohammed Beladgham , Abdesselam Bassou , Ismahane Benyahia
In biometric systems, compression takes important place especially in order to reduce the size of the information stored or transmitted through the distributed biometric systems. It is also noted that the compression techniques induce loss of information in the compressed images that can affect the effectiveness of biometric systems. The main objective of our contribution is to examine the efficacy of the used method to offer an optimal compression quality in these kind of images without considerable distortion. In order to evaluate the efficacy of the compression process, we use two kinds of evaluation, full-reference image quality assessment and a new proposed textural quality analysis of the compressed images. In this paper, we use a second-generation wavelet transform to improve the compression study in biometric images. The basic idea of this algorithm is the quincunx wavelet transform coupled to a modified progressive encoder called SPIHT-Z encoding.
Volume: 19
Issue: 3
Page: 1325-1339
Publish at: 2020-09-01

Systematic review on event prediction models

10.11591/ijeecs.v19.i3.pp1490-1496
Fakhruzy Shakirin Jamaludin , R Kanesaraj Ramasamy
Predicting an event can comes as a huge advantage for a lot of people, especially if it involves profits that a company can make. In this paper, matters that were discussed were the algorithms used for the event prediction systems, the type of algorithms and the comparison between different types of algorithm. Two main categories that were compared was the single algorithm for the prediction model and hybrid algorithms which is a combination of two or more algorithms in the model. Hybrid algorithm shows signs of better efficiency when data used were complex and large but a smaller dataset is more suitable with a single algorithm as the base as it is easier to apply with satisfactory results.
Volume: 19
Issue: 3
Page: 1490-1496
Publish at: 2020-09-01

Lighting control network based on KNX protocol, for the reduction of energy consumption

10.11591/ijeecs.v19.i3.pp1186-1193
Omar Chamorro Atalaya , Angel Quesquen-Porras , Dora Arce Santillan
This article presents the development of a lighting control network to reduce the energy consumption of a commercial building, using the KNX protocol; because of the high rates of electricity consumption, the same that are reflected in the payment of the electricity supply. For this, the design of the network architecture is carried out, the tree type quality and it has KNX, DALI components and LED luminaires, which are interconnected by means of an Ethernet type BUS; The KNX protocol configuration is then performed using the ETS version 5 software; carries out the implementation of KNX technology, determines the reduction of energy consumption by 82.33%. Likewise, emissions of carbon dioxide (CO2), one of the main gases involved in climate change, were reduced by 85%. With these results we obtain economic and environmental benefits; Reason why it is proposed to perform the same procedure for the control of air conditioning systems, since their operation represents 32.8% of the energy consumption of an establishment.
Volume: 19
Issue: 3
Page: 1186-1193
Publish at: 2020-09-01

Fault analysis in power system using power systems computer aided design

10.11591/ijaas.v9.i3.pp171-179
Fortune Chukwuebuka Amanze , Amanze Destiny Josiah
This work presents a fault analysis simulation model of an IEEE 30 bus system in a distribution network. This work annalysed the effect of fault current and fault voltage in a distribution system. A circuit breaker was introduced into the system to neutralize the effect of the fault. The system was run on a PSCAD software and results were obtained. The system was monitored based on the start time and the end time of the fault and how well the circuit breaker reacts with those times. Fault occurred from 0.100 to 0.300 seconds before it was removed. At the time fault was not applied (i.e. from 0.00 to 0.100 and from 0.300 to 0.72), the circuit breaker was close and became open when fault was applied so as to cut off current flow through the line.The result obtained gave the disruption caused by the fault and the quick response of the circuit breaker in neutralizing it. Results gotten are based on when the circuit breaker is close and no fault is applied and when the circuit breaker is open due to fault. From this work, it was obtained that circuit breakers are very essential in system protection and reliability.
Volume: 9
Issue: 3
Page: 171-179
Publish at: 2020-09-01

Performance comparison of field oriented control based permanent magnet synchronous motor fed by matrix converter using PI and IP speed controllers

10.11591/ijeecs.v19.i3.pp1156-1168
Mohamed Bouazdia , Mohamed Bouhamida , Rachid Taleb , Mouloud Denai
This paper focuses on modeling and closed-loop speed control of a three-phase Permanent Magnet Synchronous Motor (PMSM) fed by a Matrix Converter (MC) based on Field-Oriented Control (FOC). The model considers a set of a small input filter with supply impedance or cable effect, to improve the quality of the input current. A simplified form of the Venturini modulation algorithm is used for switching the matrix converter and a comparative study of two types of speed controllers is presented, namely a proportional integral (PI) and a proportional integral (PI) to improve performances of the drive system in transient and stable conditions. The overall drive system is simulated using Matlab/Simulink environment. The motor performance is evaluated under different operating conditions such as sudden changes in the load or changes in the angular speed reference. The results of the converter MC gives unlimited output frequency, sinusoidal input current and output voltage waveforms and unity input displacement factor. The IP controller is shown to achieve better performance of the speed control loop, with or without the load torque as compared to the PI classic controller.
Volume: 19
Issue: 3
Page: 1156-1168
Publish at: 2020-09-01

IoT blood pressure monitoring system

10.11591/ijeecs.v19.i3.pp1384-1390
Norlezah Hashim , Nurbahirah Norddin , Fakrulradzi Idris , Siti Nur Ilmani Mohd Yusoff , Madiha Zahari
The number of patients in hospital keep increasing every year and, some patients’s blood pressure must be measured by medical staff regularly. This means that the medical staff need to attend to the patient routinely and several readings are required in each session to make sure the results are accurate. Therefore, there is a need to simplify the monitoring process inside hospital in Malaysia. In this work, IoT blood pressure monitoring system (IBPMS) is designed to monitor patient’s blood pressure remotely. This project use Raspberry Pi as a gateway to view the value of blood pressure online. Result showed that the design is capable to transfer data from blood pressure detector through the network using USB TTL serial cable which is directly attached to the Raspberry Pi. User can also view the blood pressure reading continuously from Telegram application and email service. Furthermore, the system can measure the value of blood pressure accurately when user is in sitting position.
Volume: 19
Issue: 3
Page: 1384-1390
Publish at: 2020-09-01

Design of a contactless body temperature measurement system using Arduino

10.11591/ijeecs.v19.i3.pp1251-1258
Asif A. Rahimoon , Mohd Noor Abdullah , Ishkrizat Taib
The recent advances in electronics and microelectronics devices allow the development of newly low-cost monitoring tools used by peoples for health preventive purposes. Sensors used in medical equipments convert various forms of human body vital signs into electrical signals. Therefore, the healthcare monitoring systems considering non-invasive and wearable sensors with integrated communication mediums allow an efficient solution to live a comfortable home life.  This paper presents the remote monitoring of human body temperature (HBT) wirelessly by means of Arduino controller with different sensors and open source internet connection. The proposed monitoring system uses an internet network via wireless fieldity (wifi) connection to be linked with online portal on smart phone or computer. The proposed system is comprised of an Arduino controller, LM-35 (S1), MLX-90614 (S2) temperature sensors and ESP-wifi shield module. The obtained result has shown that real time temperature monitoring data can be transferred to authentic observer by utilizing internet of things (IoT) applications. The findings from this research indicates that the difference of average temperature in between Sensor S1 and S2 is about 15 0C
Volume: 19
Issue: 3
Page: 1251-1258
Publish at: 2020-09-01

Differential evolution algorithm of soft island model based on K-means clustering

10.11591/ijeecs.v19.i3.pp1548-1555
Xujie Tan , Seong-Yoon Shin
Differential evolution (DE) is a highly effective evolutionary algorithm. However, the performance of DE depends on strategies and control parameters. The combination of many strategies helps balance the exploitation and exploration of DE. In this study, a multi-population based on k-means clustering is proposed to realize an ensemble of multiple strategies, thereby resulting in a new DE variant, namely KSDE, where similar individuals in the population implement the same mutation strategies, and dissimilar subpopulations migrate information through the soft island model (SIM). Firstly, the population is virtually divided into k subpopulations by the k-means clustering algorithm. Secondly, the individual specific mutation scheme is selected from a strategy pool by random method. Finally, the migration of subpopulation information is done using soft island model. The performance of the KSDE algorithm is evaluated on 13 benchmark problems. The experiments show that KSDE algorithm improves the performance of the DE algorithm.
Volume: 19
Issue: 3
Page: 1548-1555
Publish at: 2020-09-01
1 2 3
...
1994 1995
Show 1087 of 1995

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