Articles
9,226 Documents
A review on data clustering using spiking neural network (SNN) models
Siti Aisyah Mohamed;
Muhaini Othman;
Mohd Hafizul Afifi
Indonesian Journal of Electrical Engineering and Computer Science Vol 15, No 3: September 2019
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v15.i3.pp1392-1400
The evolution of Artificial Neural Network recently gives researchers an interest to explore deep learning evolved by Spiking Neural Network clustering methods. Spiking Neural Network (SNN) models captured neuronal behaviour more precisely than a traditional neural network as it contains the theory of time into their functioning model [1]. The aim of this paper is to reviewed studies that are related to clustering problems employing Spiking Neural Networks models. Even though there are many algorithms used to solve clustering problems, most of the methods are only suitable for static data and fixed windows of time series. Hence, there is a need to analyse complex data type, the potential for improvement is encouraged. Therefore, this paper summarized the significant result obtains by implying SNN models in different clustering approach. Thus, the findings of this paper could demonstrate the purpose of clustering method using SNN for the fellow researchers from various disciplines to discover and understand complex data.
Traffic Prediction Based on SVM Training Sample Divided by Time
Lingli Li;
Hongxia Xia;
Lin Li;
Qingbo Wang
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 12: December 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
In recent years, the volume of traffic is rapidly increasing. When vehicles running through the tunnel are more intensive or move slowly, the tunnel environment occurs deteriorated sharply, which affects the normal operation of the vehicle in the tunnel. This paper uses the result of previous mining association rules to select feature items and to establish four training samples divided by time. Then the training samples are utilized to create the SVM classification model. Finally the trained SVM model is used to prediction the tunnel traffic situation. Through traffic situation prediction, effective decisions can be made before traffic jams, and ensure that the tunnel traffic is normal. DOI: http://dx.doi.org/10.11591/telkomnika.v11i12.3656
Internet of Things as Intimating for Pregnant Women’s Healthcare: An Impending Privacy Issues
Mir Sajjad Hussain Talpur;
Murtaza Hussain Shaikh;
Riaz Ali Buriro;
Hira Sajjad Talpur;
Fozia Talpur;
Hina Shafi;
Munazza Ahsan Shaikh
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 6: June 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Ingeniously, the innovations are taking place in current medical era, where IoT is a key and its related technology plays a dynamic role in pregnant women care taking inside hospital and outside. IoT ensure the effective and efficient care of pregnant women in any environment because intelligent tiny devices like RF-Tags, sensors are attached with pregnant women, and all the activities of pregnant women can be monitored by professional medical staff from anywhere and anytime. The usage of these advanced technologies in pregnant women care environment, absolutely eradicates the pregnancy complications and harmful incidents, but also raises privacy, religious, ethical, legal and social issues. The purpose of this paper is to discuss the usage of IoT in pregnant women healthcare environments and articulates endorsements to promote research then can guarantee that the pregnant women’s privacy is preserved. DOI : http://dx.doi.org/10.11591/telkomnika.v12i6.4227
Analysis Vehicle TWC Light-off Characteristics on AMESim Platform
Zhuang Wen Wu
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 2: February 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Though building an AMESim physical model of vehicle three-way catalytic converter (TWC), this article aims to study the light-off characteristics of TWC. By solving the energy and mass conservation equations of gas-solid two phase of the model, this article obtains the emissions conversion rate, such as CO, unburned hydrocarbons (CaHb) and nitrogen oxides (NOx) under different parameters. The results show that, the TWC light-off characteristics can be affected by the engine control strategy, allocation of TWC and the structure of TWC carrier.DOI: http://dx.doi.org/10.11591/telkomnika.v11i2.1476
Force Multiplier Effect of Futuristic Battlefield Preparedness by Adapting the Internet of Things (IoT) Concept
G Kannan;
N Manoharan
Indonesian Journal of Electrical Engineering and Computer Science Vol 9, No 2: February 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v9.i2.pp316-321
The present-day Battlefield environment depicts a scenario wherein various heterogeneous warfighting vehicles/equipment are conglomerated, and the high command takes a decision based on the different inputs and data received from the warfighting entities. This aspect generates voluminous data and communication directives occupying the complete frequency spectrum and moving up and down. This paper proposes a scheme based on the Internet of Things (IoT) philosophy. The primary focus will be to deploy ubiquitous sensing enabled technologies (IoT) in all the battlefield fighting entities. This medium in effect means the interconnection of uniquely identifiable embedded computing-like devices and formulation of an internet infrastructure. The newly proposed IoT devices in all the battlefield fighting entities will gather, infer and understand in-situ commands and data and in turn pass on to the highest decision-making authority. A simple IoT based model will be deployed in the battlefield scenario enhancing the force multiplier effect.
Optimal sizing and location of distributed generation for loss minimization using firefly algorithm
Muhamad Najib Kamarudin;
Tengku Juhana Tengku Hashim;
AbdulHamid Musa
Indonesian Journal of Electrical Engineering and Computer Science Vol 14, No 1: April 2019
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v14.i1.pp421-427
Distributed generation (DG) plays an important role in improving power quality as well as system realibility. As the incorporation of DG in the power distribution network creates several problems to the network operators, locating a suitable capacity and placement for DG will essentially help to improve the quality of power delivery to the end users. This paper presents the simulation of an application of firefly algorithm (FA) for optimally locating the most suitable placement and capacity of distributed generation (DG) in IEEE 33-bus radial distribution network. This strategy aims at minimizing losses together with improving the voltage profile in distribution network. The losses in real power and voltages at each bus are obtained using load flow analysis which was performed on an IEEE 33-bus radial distribution network using forward sweep method. The proposed method comprises of simulation of the test system with DG as well as in the absence of DG in the system. A comparison between the Firefly Algorithm (FA) with Genetic Algorithm (GA) is also demonstrated in this paper. The results obtained have proven that the Firefly Algorithm has a better capability at improving both the voltage profile and the power losses in the system.
Infrared Image Segmentation using Adaptive FCM Algorithm Based on Potential Function
Jin Liu;
Haiying Wang;
Shaohua Wang
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 8: August 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v12.i8.pp6230-6237
Traditional Fuzzy C-means segmentation algorithm requires to set clustering number in advance, and to calculate image clustering center by the iterative arithmetic. So the traditional algorithm is sensitive to the initial value and the computation complexity is high. In order to improve the traditional Fuzzy C-means algorithm, this paper presents an infrared image segmentation method using adaptive Fuzzy C-means algorithm based on potential function. The presented algorithm can directly determine the optimal clustering number and clustering center for infrared image to be segmented by the potential function. After calculating the membership matrix of pixels in the infrared image by the fuzzy theory, the final segmented image is obtained through the fuzzy clustering. The experiments show that the presented algorithm in the paper could determine the optimal clustering number of the infrared image adaptively, and ensure the accuracy of segmentation, while significantly reducing the computation speed and complexity of the algorithm.
Application of Adaptive Fuzzy PID Leveling Controller
Ke Zhang;
Jingxian Qin;
Jia Sun;
Shizhong Chen;
Yuhou Wu
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 5: May 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Aiming at the levelling precision, speed and stability of suspended access platform, this paper put forward a new adaptive fuzzy PID control levelling algorithm by fuzzy theory. The method is aided design by using the SIMULINK toolbox of MATLAB, and setting the membership function and the fuzzy-PID control rule. The levelling algorithm can real-time adjust the three parameters of PID according to the fuzzy rules due to the current state. It is experimented, which is verified the algorithm have better stability and dynamic performance. DOI: http://dx.doi.org/10.11591/telkomnika.v11i5.2563
Information Dissemination and Control Models in Complex Network
Li Juan;
Zhou Xueguang;
Chen Bin
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 12: December 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
In order to well understand and control the information dissemination in the complex network, Increasing Trust SI model and SIP model have been built to represent the peoples' interaction during information dissemination. By introducing and computing the trust degree of the net nodes, the process of information dissemination can be truly represented following increasing trust rule. Simulation experiments reveal that the informations can be quickly broken out in ER model, NW model and BA model due to the small world characteristic of complex networks. To prevent bad information disseminating, SIP model with "Persuasion" mechanism is presented. It can be effect when immune nodes with "P" status persuade their neighber disseminator with the truth. Simulation experiments show that not all nodes in the network will be disseminated and all will lose the trust on the bad information. Exceptionally, the best effection is in BA network with free-scale. The results of this paper can be used for analysis and management of information dissemination on complex networks.DOI: http://dx.doi.org/10.11591/telkomnika.v11i12.3662
Capacitive Sensing Algorithm for Elderly Activity Detection Scheme Indoor Environment
Atika Arshad;
Sheroz Khan;
Kushsairy Abdul Kadir;
Rumana Tasnim
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 2: August 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v11.i2.pp515-521
The aim of this research is to assist elderlies in accomplishing their everyday tasks through facilitating their home atmosphere with sensors, actuators, and computational resources. A significant effort is needed to incorporate them to make them effective in daily life. Particularly, the tracking and detection of elderly people’s daily tasks, associated with the information of the user's location in the home environment signify the key pillars of this work. The detecting and tracking algorithm uses the sensory data to indicate an associated situation in order to allow elderly people with special requirements. Monitoring the elderly’s behaviour over a long period of time will allow prediction of their forthcoming alarming situation which allows the finding of the elderly’s behavioural deviations in their everyday routine. The proposed resolution has been methodically assessed in the laboratory.