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

29,734 Article Results

Hybrid backpropagation neural network-particle swarm optimization for seismic damage building prediction

10.11591/ijeecs.v14.i1.pp360-367
Marina Yusoff , Faris Mohd Najib , Rozaina Ismail
The evaluation of the vulnerability of buildings to earthquakes is of prime importance to ensure a good plan can be generated for the disaster preparedness to civilians. Most of the attempts are directed in calculating the damage index of buildings to determine and predict the vulnerability to certain scales of earthquakes. Most of the solutions used are traditional methods which are time consuming and complex. Some of initiatives have proven that the artificial neural network methods have the potential in solving earthquakes prediction problems. However, these methods have limitations in terms of suffering from local optima, premature convergence and overfitting. To overcome this challenging issue, this paper introduces a new solution to the prediction on the seismic damage index of buildings with the application of hybrid back propagation neural network and particle swarm optimization (BPNN-PSO) method. The prediction was based on damage indices of 35 buildings around Malaysia. The BPNN-PSO demonstrated a better result of 89% accuracy compared to the traditional backpropagation neural network with only 84%. The capability of PSO supports fast convergence method has shown good effort to improve the processing time and accuracy of the results.
Volume: 14
Issue: 1
Page: 360-367
Publish at: 2019-04-01

An intelligent approach to take care of mother and baby health

10.11591/ijece.v9i2.pp1137-1144
Mohammad Nasser Uddin , Mohammad Jahangir Alam , Md. Nurul Mustafa
This is the era of technology and is widely used in every sector. In Bangladesh the use of technology is increasing day by day in many sectors. Health sector is one of them. This research is designed and developed to help the pregnant women to get weekly information on development and conditions of their health and the growing child inside their womb. This system will notify expectant mothers automatically   about their health checkup date and time. It provides general and special health information to the expectant mothers. It is designed with user friendly interface so that an expectant mother can use this system very effectively. This system allows a unique secure login system and provides a unique suggestion to the expectant mothers.This system is very user friendly and useful.
Volume: 9
Issue: 2
Page: 1137-1144
Publish at: 2019-04-01

Elastic neural network method for load prediction in cloud computing grid

10.11591/ijece.v9i2.pp1201-1208
Kefaya S. Qaddoum , Nameer N. El Emam , Mosleh A. Abualhaj
Cloud computing still has no standard definition, yet it is concerned with Internet or network on-demand delivery of resources and services. It has gained much popularity in last few years due to rapid growth in technology and the Internet. Many issues yet to be tackled within cloud computing technical challenges, such as Virtual Machine migration, server association, fault tolerance, scalability, and availability. The most we are concerned with in this research is balancing servers load; the way of spreading the load between various nodes exists in any distributed systems that help to utilize resource and job response time, enhance scalability, and user satisfaction. Load rebalancing algorithm with dynamic resource allocation is presented to adapt with changing needs of a cloud environment. This research presents a modified elastic adaptive neural network (EANN) with modified adaptive smoothing errors, to build an evolving system to predict Virtual Machine load. To evaluate the proposed balancing method, we conducted a series of simulation studies using cloud simulator and made comparisons with previously suggested approaches in the previous work. The experimental results show that suggested method betters present approaches significantly and all these approaches.
Volume: 9
Issue: 2
Page: 1201-1208
Publish at: 2019-04-01

A cost effective computational design of maximum power point tracking for photo-voltaic cell

10.11591/ijece.v9i2.pp851-860
Yoganandini A. P. , Anitha G. S.
Maximum Power Point Tracking (MPPT) is one of the essential controller operations of any Photo-Voltaic (PV) cell design. Developing an efficient MPPT system includes a significant challenge as there are various forms of uncertainty factors that results in higher degree of fluctuation in current and voltage in PV cell. After reviewing existing system, it has been found that there is no presence of any benchmarked model to ensure a better form of computational model. Hence, this paper presents a novel and very simple design of MPPT without using any form of complex design mechanism nor including any form of frequently used iterative approach. The proposed model is completely focused on developing an algorithm that takes the input of voltage (open circuit), current (short circuit), and max power in order to obtain the peak power to be extracted from the PV cells. The study outcome shows faster response time and better form of analysis of current-voltage-power for given state of PV cells.
Volume: 9
Issue: 2
Page: 851-860
Publish at: 2019-04-01

Linearity improvement of differential CMOS low noise amplifier

10.11591/ijeecs.v14.i1.pp407-412
Maizan Muhamad , Norhayati Soin , Harikrishnan Ramiah
This paper presents the linearity improvement of differential CMOS low noise amplifier integrated circuit using 0.13um CMOS technology. In this study, inductively degenerated common source topology is adopted for wireless LAN application. The linearity of the single-ended LNA was improved by using differential structures with optimum biasing technique. This technique achieved better LNA and linearity performance compare with single-ended structure. Simulation was made by using the cadence spectre RF tool. Consuming 5.8mA current at 1.2V supply voltage, the designed LNA exhibits S21 gain of 18.56 dB, noise figure (NF) of 1.85 dB, S11 of −27.63 dB, S22 of -34.33 dB, S12 of −37.09 dB and IIP3 of -7.79 dBm.
Volume: 14
Issue: 1
Page: 407-412
Publish at: 2019-04-01

Single view vs. multiple views scatterplots

10.11591/ijece.v9i2.pp1426-1436
Federico Manuri , Andrea Sanna , Fabrizio Lamberti
Among all the available visualization tools, the scatterplot has been deeply analyzed through the years and many researchers investigated how to improve this tool to face new challenges. The scatterplot visualization diagram is considered one of the most functional among the variety of data visual representations, due to its relative simplicity compared to other multivariable visualization techniques. Even so, one of the most significant and unsolved challenge in data visualization consists in effectively displaying datasets with many attributes or dimensions, such as multidimensional or multivariate ones. The focus of this research is to compare the single view and the multiple views visualization paradigms for displaying multivariable dataset using scatterplots. A multivariable scatterplot has been developed as a web application to provide the single view tool, whereas for the multiple views visualization, the ScatterDice web app has been slightly modified and adopted as a traditional, yet interactive, scatterplot matrix. Finally, a taxonomy of tasks for visualization tools has been chosen to define the use case and the tests to compare the two paradigms.
Volume: 9
Issue: 2
Page: 1426-1436
Publish at: 2019-04-01

Impact of gamma-ray irradiation on dynamic characteristics of Si and SiC power MOSFETs

10.11591/ijece.v9i2.pp1453-1460
Ramani Kannan , Saranya Krishnamurthy , Chay Che Kiong , Taib B Ibrahim
Power electronic devices in spacecraft and military applications requires high radiation tolerant. The semiconductor devices face the issue of device degradation due to their sensitivity to radiation. Power MOSFET is one of the primary components of these power electronic devices because of its capabilities of fast switching speed and low power consumption. These abilities are challenged by ionizing radiation which damages the devices by inducing charge built-up in the sensitive oxide layer of power MOSFET. Radiations degrade the oxides in a power MOSFET through Total Ionization Dose effect mechanism that creates defects by generation of excessive electron–hole pairs causing electrical characteristics shifts. This study investigates the impact of gamma ray irradiation on dynamic characteristics of silicon and silicon carbide power MOSFET. The switching speed is limit at the higher doses due to the increase capacitance in power MOSFETs. Thus, the power circuit may operate improper due to the switching speed has changed by increasing or decreasing capacitances in power MOSFETs. These defects are obtained due to the penetration of Cobalt60 gamma ray dose level from 50krad to 600krad. The irradiated devices were evaluated through its shifts in the capacitance-voltage characteristics, results were analyzed and plotted for the both silicon and silicon carbide power MOSFET.
Volume: 9
Issue: 2
Page: 1453-1460
Publish at: 2019-04-01

An ensemble multi-model technique for predicting chronic kidney disease

10.11591/ijece.v9i2.pp1321-1326
Komal Kumar N , R. Lakshmi Tulasi , Vigneswari D
Chronic Kidney Disease (CKD) is a type of lifelong kidney disease that leads to the gradual loss of kidney function over time; the main function of the kidney is to filter the wastein the human body. When the kidney malfunctions, the wastes accumulate in our body leading to complete failure. Machine learning algorithms can be used in prediction of the kidney disease at early stages by analyzing the symptoms. The aim of this paper is to propose an ensemble learning technique for predicting Chronic Kidney Disease (CKD). We propose a new hybrid classifier called as ABC4.5, which is ensemble learning for predicting Chronic Kidney Disease (CKD). The proposed hybrid classifier is compared with the machine learning classifiers such as Support Vector Machine (SVM), Decision Tree (DT), C4.5, Particle Swarm Optimized Multi Layer Perceptron (PSO-MLP). The proposed classifier accurately predicts the occurrences of kidney disease by analysis various medical factors. The work comprises of two stages, the first stage consists of obtaining weak decision tree classifiers from C4.5 and in the second stage, the weak classifiers are added to the weighted sum to represent the final output for improved performance of the classifier.
Volume: 9
Issue: 2
Page: 1321-1326
Publish at: 2019-04-01

Compact modeling of strained GAA SiNW

10.11591/ijeecs.v14.i1.pp241-249
Fatimah K. A Hamid , N. Ezaila Alias , R. Ismail , M. Anas Razali
Strain-based on advanced MOSFET is a promising candidate for the future of CMOS technology. A numerical model is not favorable compared to a compact model because it cannot be integrated into most simulator software. Thus, a compact model is proposed to overcome the shortcomings in the analytical model. In this paper, a charge-based compact model is presented for long-channel strained Gate-All-Around Silicon Nanowire (GAA SiNW) from an undoped channel to a doped body. The model derivation is based on an inversion charge which has been solved explicitly using the smoothing function. The drain current model is formulated from Pao Sah’s dual integral which is formed in terms of inversion charge at the drain and source terminals. The proposed model has been extensively verified with the numerical simulator data. The strained effect on the electrical parameters are studied based on inversion charge, threshold voltage and current-voltage (I-V) characteristics. Results show that the current, the inversion charge and the threshold voltage can be greatly improved by the strain. The threshold voltage was reduced approximately 40% from the conventional GAA SiNW. Moreover, the inversion charge was improved by 30 % and the on-state current has doubled compared to unstrained device.
Volume: 14
Issue: 1
Page: 241-249
Publish at: 2019-04-01

Renewable microgrid operational results and economic evaluation using RETScreenTM

10.11591/ijece.v9i2.pp723-731
Edison Banguero , Hector David Agudelo Arias , Andres Julian Aristizabal , Daniel Hernán Ospina Baragán
This article describes the performance results of the first renewable microgrid of Chocó, Colombia, monitored over two years (2016-2017) adding an economic approach. A virtual platform is used to analyze, in real time, the microgrid power production, while a meteorological station measures the solar irradiance and the ambient temperature. The results indicated that the generation of AC PV energy was 21,817 kWh/year on 2016 and 23,301 kWh/year on 2017. The photovoltaic system’s average efficiency was 10.3 % on 2016 and 11.09 % on 2017. An economical analysis of the renewable microgrid is also presented using RETScreenTM software. The results show a net present value of $237,028 USD for an evaluation period of 25 years with annual energy savings of $4,622 USD. A calculation on greenhouse gas emissions show that 22.9 tCO2 per year are avoided  when using the solar energy tech.
Volume: 9
Issue: 2
Page: 723-731
Publish at: 2019-04-01

Genetic-fuzzy based load balanced protocol for WSNs

10.11591/ijece.v9i2.pp1168-1183
Pankaj Kumar Kashyap , Sushil Kumar
Recent advancement in wireless sensor networks primarily depends upon energy constraint. Clustering is the most effective energy-efficient technique to provide robust, fault-tolerant and also enhance network lifetime and coverage. Selection of optimal number of cluster heads and balancing the load of cluster heads are most challenging issues. Evolutionary based approach and soft computing approach are best suitable for counter the above problems rather than mathematical approach. In this paper we propose hybrid technique where Genetic algorithm is used for the selection of optimal number of cluster heads and their fitness value of chromosome to give optimal number of cluster head and minimizing the energy consumption is provided with the help of fuzzy logic approach. Finally cluster heads uses multi-hop routing based on A*(A-star) algorithm to send aggregated data to base station which additionally balance the load. Comparative study among LEACH, CHEF, LEACH-ERE, GAEEP shows that our proposed algorithm outperform in the area of total energy consumption with various rounds and network lifetime, number of node alive versus rounds and packet delivery or packet drop ratio over the rounds, also able to balances the load at cluster head.
Volume: 9
Issue: 2
Page: 1168-1183
Publish at: 2019-04-01

Indonesian online travel agent sentiment analysis using machine learning methods

10.11591/ijeecs.v14.i1.pp113-117
Abimanyu Dharma Poernomo , Suharjito Suharjito
Many companies use social media to support their business activities. Three leading online travel agent such as Traveloka, Tiket.com, and Agoda use Facebook for supporting their business as customer service tool. This study is to measure customer satisfaction of Traveloka, Tiket.com, and Agoda by analyzing Facebook posts and comments data from their fan pages. That data will be analyzed with three machine learning algorithms such as K-Nearest Neighbors (KNN), Naïve Bayes, and Support Vector Machine (SVM) to determine the sentiment.  From the classification results, data will be selected with the highest f-score to be used to calculate the Net Sentiment Score used to measure customer satisfaction. The result shows that KNN result better than Naive Bayes and SVM based on f-score. Based on Net Sentiment Score shows companies that get the highest satisfaction value of Traveloka followed by Tiket.com and Agoda
Volume: 14
Issue: 1
Page: 113-117
Publish at: 2019-04-01

Smart halal recognizer for muslim consumers

10.11591/ijeecs.v14.i1.pp193-200
Siti Fatimah Abdul Razak , Chin Poo Lee , Kian Ming Lim , Pei Xin Tee
Halal is the term used for permissible food according to Islamic dietary law. Indicators such as Halal logo have been used to facilitate Muslims in identifying Halal food. In Malaysia, the Department of Islamic Development (JAKIM) has introduced a standard Halal logo for locally manufactured products and currently recognizes 67 Islamic bodies in 41 countries around the world as certification bodies for products imported into Malaysia. Therefore, a more practical way is required to assist Muslims in recognizing various forms of Halal logos on food packaging. A neural network (NN) approach is proposed to recognize authentic and recognized Halal logo on imported products. A dataset of available and recognized Halal logo images worldwide will be created for this purpose. The dataset will be used to train and test the performance of the learning algorithm to recognize logo of recognized foreign bodies by JAKIM. The approach is expected to complement current facilities for verification using Short Messaging Services (SMS) and web portal. The approach is assumed to be more efficient and accurate for Halal logo verification which eventually could win the trust of Halal product consumers and support the Halal industry in Malaysia.
Volume: 14
Issue: 1
Page: 193-200
Publish at: 2019-04-01

Compared to wireless deployment in areas with different environmentse

10.11591/ijece.v9i2.pp934-940
Inaam Abbas Hieder
In the mobile phone system, it is highly desirable to estimate the loss of the track not only to improve performance but also to achieve an accurate estimate of financial feasibility; the inaccurate estimate of track loss either leads to performance degradation or increased cost. Various models have been introduced to accurately estimate the path loss. One of these models is the Okomura / Hata model, which is recommended for estimating path loss in cellular systems that use micro cells. This system is suitable for use in a variety of environments. This study examines the comparison of path loss models for statistical analysis derived from experimental data collected in urban and suburban areas at frequencies of 150-1500 MHz’s The results of the measurements were used to develop path loss models in urban and suburban areas. The results showed that Pathloss increases in urban areas respectively.
Volume: 9
Issue: 2
Page: 934-940
Publish at: 2019-04-01

BER analysis of concatenated levels of encoding in GFDM system using labview

10.11591/ijeecs.v14.i1.pp77-87
Nagarjuna Telagam , S Lakshmi , K Nehru
All the devices are interconnected each other in digital form, for different applications the input data is encoded for error correcting and detecting purpose. The paper describes the transmission of QAM signals with two level encoded stages, i.e. convolutional and hamming coded GFDM system with 256-point IFFT at transmitter and FFT at the receiver using LABVIEW software. GFDM is a non-orthogonal, digital multicarrier transmission scheme which digitally implements the classical filter bank approach. GFDM transmits a block of frame composed by M time slots with K subcarriers. The higher order QAM is used because of transmitting more data but is less reliable when compared to lower order QAM. Based on GFDM specifications for the IEEE 802.11, latest 5G physical layer standards, the coding is provided by ½ rate encoder at the input side, and Maximum Likelihood decoder at the receiver side is used. The standard convolution code (7, [171, 133]), is used as encoder for the GFDM system. The GFDM complex values are displayed in the front panel, along with FFT and power spectrum is plotted for GFDM signal. The array of input bits and output bits are shown with green colour LED’s. The van de Beek algorithm is used at the receiver for maximum likelihood detection acts as convolutional decoder of GFDM signal. Next the signal is subjected to remove cyclic prefix and zero padding and applied to channel estimation algorithm. The un-equalized data and equalized data graph is shown in the front panel, before and after channel estimation VI. With BER VI available in the LABVIEW the data is normalized and its response is plotted with respect to SNR. BER values for different levels of encoders have shown in table for SNR values. This paper concludes the 32.91% improvement in BER for two levels of concatenated codes.Thus the GFDM signal outperforms the OFDM signal interms of BER for series levels of coding using labVIEW software.
Volume: 14
Issue: 1
Page: 77-87
Publish at: 2019-04-01
1 2 3
...
1982 1983
Show 1303 of 1983

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