scispace - formally typeset
Search or ask a question

Showing papers in "Indonesian Journal of Electrical Engineering and Computer Science in 2019"


Journal ArticleDOI
TL;DR: In this article, the authors have outlined numerical investigation of V shaped three element resonator and the stability parameter is measured against back mirror curvature radius, back mirror phase angle, focusing length, focusing mirror phase angles, folding range in both S plane and T plane.
Abstract: This study have outlined numerical investigation of V shaped three element resonator. The stability parameter is measured against back mirror curvature radius , back mirror phase angle , focusing length , focusing mirror phase angle , folding range in both S plane and T plane. The stability parameter is changed in positive and negative trend under the operating system parameters. The stability parameter should be optimized in order to achieve high performance efficiency of resonator system. Beam radius variations are also measured versus focusing range , folding range, and back mirror phase angle. It is clear that the negative effects of increasing system parameters on beam radius variation in both S plane and T plane.

89 citations


Journal ArticleDOI
TL;DR: In this paper, a simulative study of simple ring resonator based Brewster plate in the air is presented, and the results are achieved with the variations of space length, curvature radius and phase angle of the spherical mirror.
Abstract: This study has outlined the simulative study of simple ring resonator based Brewster plate in the air. The obtained results are achieved with the variations of space length, curvature radius and phase angle of the spherical mirror . Beam radius criterion and stability parameters are measured with the variations of refractive index and thickness of Brewster plate in the air. The negative and positive effects of increasing operating parameters are observed on the performance of ring resonator system efficiency.

83 citations


Journal ArticleDOI
TL;DR: In this article, a basic and adaptable remote arrange for domestics computerization of temperature, moistness, gas, movement and light by executing dependable sensor hubs which can be controlled too observed.
Abstract: Security is one of the imperative issues in an advanced local condition. The current center around formative and research issues of Wireless Sensor Network(WSN) based Smart Home. WSN based shrewd home detection system gives a safe and safe living condition. A Wireless Sensor System (WSN) is a system which is building by utilizing little independent hubs (sensors). Its motivation is to screen certain ecological parameters, for example, temperature, dampness, brilliance, weight, sound, movement, and so forth. This paper depicts the improvement of a smart home condition dependent on exact Wireless Sensor Network and furthermore depicts private vitality observing and controlling procedures for keen home systems administration framework. This paper proposes a basic and adaptable remote arrange for domestics computerization of temperature, moistness, gas, movement and light by executing dependable sensor hubs which can be controlled too observed. This innovation offers energizing and new chance to build the availability of devices inside the home for the home computing.

70 citations


Journal ArticleDOI
TL;DR: A comprehensive survey is performed to identify the challenges of handling imbalanced class problems during classification process using machine learning algorithms and the viable solutions and potential future directions are provided to handle the problems.
Abstract: The imbalanced data problems in data mining are common nowadays, which occur due to skewed nature of data. These problems impact the classification process negatively in machine learning process. In such problems, classes have different ratios of specimens in which a large number of specimens belong to one class and the other class has fewer specimens that is usually an essential class, but unfortunately misclassified by many classifiers. So far, significant research is performed to address the imbalanced data problems by implementing different techniques and approaches. In this research, a comprehensive survey is performed to identify the challenges of handling imbalanced class problems during classification process using machine learning algorithms. We discuss the issues of classifiers which endorse bias for majority class and ignore the minority class. Furthermore, the viable solutions and potential future directions are provided to handle the problems .

69 citations


Journal ArticleDOI
TL;DR: A new K-Means clustering algorithm that performs data clustering dynamically and outperforms the original K-means method on the basis of the number of clusters formed.
Abstract: Data mining is the process of finding structure of data from large data sets. With this process, the decision makers can make a particular decision for further development of the real-world problems. Several data clusteringtechniques are used in data mining for finding a specific pattern of data. The K-means method isone of the familiar clustering techniques for clustering large data sets. The K-means clustering method partitions the data set based on the assumption that the number of clusters are fixed.The main problem of this method is that if the number of clusters is to be chosen small then there is a higher probability of adding dissimilar items into the same group. On the other hand, if the number of clusters is chosen to be high, then there is a higher chance of adding similar items in the different groups. In this paper, we address this issue by proposing a new K-Means clustering algorithm. The proposed method performs data clustering dynamically. The proposed method initially calculates a threshold value as a centroid of K-Means and based on this value the number of clusters are formed. At each iteration of K-Means, if the Euclidian distance between two points is less than or equal to the threshold value, then these two data points will be in the same group. Otherwise, the proposed method will create a new cluster with the dissimilar data point. The results show that the proposed method outperforms the original K-Means method.

65 citations


Journal ArticleDOI
TL;DR: Predictive models using classification algorithm to predict student’s performance at selected university in Malaysia and results show that the Naive Bayes outperform other classification algorithm.
Abstract: Data mining approach has been successfully implemented in higher education and emerge as an interesting area in educational data mining research. The approach is intended for identification and extraction of new and potentially valuable knowledge from the data. Predictive model developed using supervised data mining approach can derive conclusion on students' academic success. The ability to predict student’s performance can be beneficial for innovation in modern educational systems. The main objective of this paper is to develop predictive models using classification algorithm to predict student’s performance at selected university in Malaysia. The prediction model developed can be used to identify the most important attributes in the data. Several predictive modelling techniques of K-Nearest Neighbor, Naive Bayes, Decision Tree and Logistic Regression Model models were used to predict student’s performance whether excellent or non-excellent. Based on accuracy measure, precision, recall and ROC curve, results show that the Naive Bayes outperform other classification algorithm. The Naive Bayes reveals that the most significant factors contributing to prediction of excellent students is when the student scores A+ and A in Multivariate Analysis; A+, A and A- in SAS Programming and A, A- and B+ in ITS 472.

40 citations


Journal ArticleDOI
TL;DR: A YouTube Spam detection framework that consists of five (5) phases such as data collection, pre-processing, features selection and extraction, classification and detection was developed and examined and validate each of the phases by using two types of data mining tool.
Abstract: YouTube has become a popular social media among the users. Due to YouTube popularity, it became a platform for spammer to distribute spam through the comments on YouTube. This has become a concern because spam can lead to phishing attack which the target can be any user that click any malicious link. Spam has its own features that can be analyzed and detected by classification. Hence, enhancement features are proposed to detect YouTube spam. In order to conduct the experiments, a YouTube Spam detection framework that consists of five (5) phases such as data collection, pre-processing, features selection and extraction, classification and detection were developed. This paper, proposed the YouTube detection framework, examined and validate each of the phases by using two types of data mining tool. The features are constructed from analysis by using data collected from YouTube Spam dataset by using Naive Bayes and Logistic Regression and tested in two different data mining tools which is Weka and Rapid Miner. From the analysis, thirteen (13) features that had been tested on Weka and RapidMiner shows high accuracy, hence is being used throughout the experiment in this research. Result of Naive Bayes and Logistic Regression run in Weka is slightly higher than RapidMiner. In addition, result of Naive Bayes is higher than Logistic Regression with 87.21% and 85.29% respectively in Weka. While in RapidMiner there is slightly different of accuracy between Naive Bayes and Logistic Regression 80.41% and 80.88%. But, precision of Naive Bayes is higher than Logistic Regression.

35 citations


Journal ArticleDOI
TL;DR: A new intelligent device is designed and utilized to control the operation of irrigation pumps using a robust method of communication to transfer information at long distances, for the lowest cost, and the longest battery life.
Abstract: Controlling electrical pumps on farms can be problematic, especially if there are a small number of people managing or working on huge areas of land and if the provision of electricity is not consistent. Therefore, further techniques for the management of plant irrigation on this type of land are being invented to make the process of irrigation easier. In this paper, a new intelligent device is designed and utilized to control the operation of irrigation pumps using a robust method of communication to transfer information at long distances, for the lowest cost, and the longest battery life. This technology is called LoRa (Long Range) communication, which is a low-power technology. The unit consists of two circuits: the first one is for switching the pumps ON and OFF, while the second one controls and monitoring the work of the pumps. Monitoring of the pumps can also be carried out through smart phones by measuring the voltage. The most important features of this new design are its intelligent control for long distances, cheap price, and a long operational life of more than five years. The goal of this paper is to help farmers by designing and manufacturing a remote-control system that switches irrigation pumps on and off using LoRa technologies.

33 citations


Journal ArticleDOI
TL;DR: This research uses the rule-based method with the help of SentiWordNet and Support Vector Machine (SVM) algorithm with Term Frequency–Inverse Document Frequency (TF-IDF) as feature extraction method for sentiment analysis in Indonesia.
Abstract: Sentiment analysis has grown rapidly which impact on the number of services using the internet popping up in Indonesia. In this research, the sentiment analysis uses the rule-based method with the help of SentiWordNet and Support Vector Machine (SVM) algorithm with Term Frequency–Inverse Document Frequency (TF-IDF) as feature extraction method. Since the number of sentences in positive, negative and neutral classes is imbalanced, the oversampling method is implemented. For imbalanced dataset, the rule-based SentiWordNet and SVM algorithm achieve accuracies of 56% and 76%, respectively. However, for the balanced dataset, the rule-based SentiWordNet and SVM algorithm achieve accuracies of 52% and 89%, respectively.

32 citations


Journal ArticleDOI
TL;DR: An automated system using Faster Region Convolutional Neural Network (Faster R-CNN) to track the position of the badminton player from the sport broadcast video revealed that the detector successfully detects the player when the detector is being fed with more generalized dataset.
Abstract: Nowadays, coaches and sport analyst are concerning about sport performance analysis through sport video match. However, they still used conventional method which is through manual observation of the full video that is very troublesome because they might miss some meaningful information presence in the video. Several previous studies have discussed about tracking ball movements, identification of player based on jersey color and number as well as player movement detection in various type of sport such as soccer and volleyball but not in badminton. Therefore, this study focused on developing an automated system using Faster Region Convolutional Neural Network (Faster R-CNN) to track the position of the badminton player from the sport broadcast video. In preparing the dataset for training and testing, several broadcast videos were converted into image frames before labelling the region which indicate the players. After that, several different trained Faster R-CNN detectors were produced from the dataset before tested with different set of videos to evaluate the detector performance. In evaluating the performance of each detector model, the average precision was obtained from precision recall graph. As a result, this study revealed that the detector successfully detects the player when the detector is being fed with more generalized dataset.

31 citations


Journal ArticleDOI
TL;DR: In this article, a session key based soft computing transmission of intraoral gingivitis image has been proposed without the exchange of common key in between the nodes, which can preserve patients' confidentiality factor.
Abstract: In this paper, a key based soft computing transmission of intraoral gingivitis image has been proposed without the exchange of common key in between the nodes. Gingivitis has been a type of periodontal disease caused due to bacterial colonization inside the mouth, having the early signs of gum bleeding and inflammations in human beings. In E-health care strata, online transmission of such intraoral images with secured encryption technique is needed. Session key based neural soft computing transmission by the dentists has been proposed in this paper with an eye to preserve patients’ confidentiality factor. To resist the data distortion by the eavesdroppers while on the transmission path, secured transmission in a group of tree parity machines was carried out. Topologically same tree parity machines with equal seed values were used by all users of that specified group. A common session key synchronization method was applied in that group. Intraoral image has been encrypted to generate multiple secret shares. Multiple secrets were transmitted to individual nodes in that group. The original gingivitis image can only be reconstructed upon the merging of threshold number of shares. Regression statistics along with ANOVA analysis were carried out on the result set obtained from the proposed technique. The outcomes of such tests were satisfactory for acceptance.

Journal ArticleDOI
TL;DR: Energy computation concept of multilayer neural network synchronized on derived transmission key based encryption system has been proposed for wireless transactions and Floating frequency analysis of the proposed encrypted stream of bits has yielded better degree of security results.
Abstract: Energy computation concept of multilayer neural network synchronized on derived transmission key based encryption system has been proposed for wireless transactions. Multilayer perceptron transmitting machines accepted same input array, which in turn generate a resultant bit and the networks were trained accordingly to form a protected variable length secret-key. For each session, different hidden layer of multilayer neural network is selected randomly and weights of hidden units of this selected hidden layer help to form a secret session key. A novel approach to generate a transmission key has been explained in this proposed methodology. The last thirty two bits of the session key were taken into consideration to construct the transmission key. Inverse operations were carried out by the destination perceptron to decipher the data. Floating frequency analysis of the proposed encrypted stream of bits has yielded better degree of security results. Energy computation of the processed nodes inside multi layered networks can be done using this proposed frame of work.

Journal ArticleDOI
TL;DR: The simulation results and security analysis have demonstrated that the proposed encryption system is robust and flexible, and the proposed crypto processor offers high security and reliable encryption speed for real-time image encryption and transmission.
Abstract: In this paper, an FPGA implementation of efficient image encryption algorithm using a chaotic map has been proposed. The proposed system consists of two phases image encryption technique. First phase consists of scrambling of pixel position and second phase consist of diffusion of bit value. In the first phase, original pixel values remain unchanged. In second phase, pixel values are modified. These modifications are done by using chaotic behavior of a recently developed chaotic map called Nahrain. A color image encryption using Nahrain chaotic map is simulated in software via Matlab, Altera Quartus Prime 17.0 Lite EditionI and ModelSim software tools then implemented in hardware via Cyclone V GX Starter Kit FPGA platform. The results show the feasibility and effectiveness of the cryptosystem. As a typical application, the image encryption/decryption is used to demonstrate and verify the operation of the cryptosystem hardware. Complete analysis on robustness of the method is investigated. Correlation, Encryption time, Decryption time and key sensitivity show that the proposed crypto processor offers high security and reliable encryption speed for real-time image encryption and transmission. To evaluate the performance, histogram, correlation, information entropy, number of pixel change rate (NPCR), and unified average changing intensity (UACI) measures are used for security analysis. The simulation results and security analysis have demonstrated that the proposed encryption system is robust and flexible. For example the amount of entropy obtained by the proposed algorithm is 7.9964, which is very close to its ideal amount: 8, and NPCR is 99.76 %, which is the excellent value to obtain. The hardware simulation results show that the number of pins that used of the proposed system reaches to 6% of total pins and Logic utilization (in ALMs) is 1%.

Journal ArticleDOI
TL;DR: A cluster-based feature selection approach to adopt more discriminative subset texture features based on three different texture image datasets and achieves better classification accuracy and performance using KNN and NB classifiers that were 99.9554% for Kelberg dataset and 99.0625% for SVM in Brodatz-1 and BrodatZ-2 datasets consecutively.
Abstract: Computer vision and pattern recognition applications have been counted serious research trends in engineering technology and scientific research content. These applications such as texture image analysis and its texture feature extraction. Several studies have been done to obtain accurate results in image feature extraction and classifications, but most of the extraction and classification studies have some shortcomings. Thus, it is substantial to amend the accuracy of the classification via minify the dimension of feature sets. In this paper, presents a cluster-based feature selection approach to adopt more discriminative subset texture features based on three different texture image datasets. Multi-step are conducted to implement the proposed approach. These steps involve texture feature extraction via Gray Level Co-occurrence Matrix (GLCM), Local Binary Pattern (LBP) and Gabor filter. The second step is feature selection by using K-means clustering algorithm based on five feature evaluation metrics which are infogain, Gain ratio, oneR, ReliefF, and symmetric. Finally, K-Nearest Neighbor (KNN), Naive Bayes (NB) and Support Vector Machine (SVM) classifiers are used to evaluate the proposed classification performance and accuracy. Research achieved better classification accuracy and performance using KNN and NB classifiers that were 99.9554% for Kelberg dataset and 99.0625% for SVM in Brodatz-1 and Brodatz-2 datasets consecutively. Conduct a comparison to other studies to give a unified view of the quality of the results and identify the future research directions.

Journal ArticleDOI
TL;DR: An adaptive mechanism that utilizes a Recursive Least Square (RLS) algorithm, with rate limiters, is implemented to perform an online self-adjusting of each of the PID gains in order to achieve Adaptive PID (APID) controller that will accommodate to system variations.
Abstract: Proportional Integral Derivative (PID) controllers are extensively used in practical industries to control the speed of DC Motors. The single weakness of PID controllers is their sensitivity to variation in parameters and operating conditions; thus, tuning the controller gains to adapt with these variations presents a practical challenge. In this paper, an adaptive mechanism that utilizes a Recursive Least Square (RLS) algorithm, with rate limiters, is implemented to perform an online self-adjusting of each of the PID gains in order to achieve Adaptive PID (APID) controller that will accommodate to system variations. MATLAB/ Simulink software is used to implement and simulate APID control of a Chopper-Fed DC motor. A conventional PID control system is also designed and simulated to obtain results that can be used to judge the performance of the APID controller. Results proved that the APID controller forced the motor speed to track the reference input with insignificant tracking error, and also managed to attain the motor speed at its desired value, regardless of the load changes inflected on the motor. This enhances both transient and steady-state speed responses.

Journal ArticleDOI
TL;DR: This work proposed the framework DEtecting Contiguous Outliers in the LOw-rank Representation for face tracking, in this algorithm the background is assessed by a low-rank network and foreground articles can be distinguished as anomalies for non-rigid foreground motion and moving camera.
Abstract: In recent times face tracking and face recognition have turned out to be increasingly dynamic research field in image processing. This work proposed the framework DEtecting Contiguous Outliers in the LOw-rank Representation for face tracking, in this algorithm the background is assessed by a low-rank network and foreground articles can be distinguished as anomalies. This is suitable for non-rigid foreground motion and moving camera. The face of a foreground person is caught from the frame and then it is contrasted and the speculated pictures stored in the dataset. Here we used Viola-Jones algorithm for face recognition. This approach outperforms the traditional algorithms on multimodal video methodologies and it works adequately on extensive variety of security and surveillance purposes. Results on the continuous demonstrate that the proposed calculation can correctly obtain facial features points. The algorithm is relegate on the continuous camera input and under ongoing ecological conditions.

Journal ArticleDOI
TL;DR: IoT Security Risk Model for Healthcare is introduced to cater a complete process of risk management based on ISO/IEC 27005:2018 standard and it is believed that by having this model, it will emphasize on iterative IoT risk management process as it may increase the depth and detail of the assessment at each iteration.
Abstract: The Internet of Things (IoT) has not been around for very long. However, since the notion of IoT introduced, most of IoT studies focused on a strategic level such as planning, architectures, standardization, and latest technologies, however, studies of risk management plan of IoT are still lacking. IoT has been widely used to link existing medical resources and provide reliable, effective and smart healthcare services to elderly and patients with chronic illnesses. However, a systematic process is missing when managing and anticipating the risk of IoT usage in healthcare. For this purpose, this paper extensively explores various IoT technologies used in health care services and its security challenges. As a result, IoT Security Risk Model for Healthcare is introduced to cater a complete process of risk management based on ISO/IEC 27005:2018 standard. It is believed that by having this model, it will emphasize on iterative IoT risk management process as it may increase the depth and detail of the assessment at each iteration.

Journal ArticleDOI
TL;DR: Current researches on the graph search algorithms under combinatorial method are mainly reviewed in this paper by keeping focus on the comprehensive surveys of its properties for path planning, resulting in a pen picture of their assumptions and drawbacks.
Abstract: Unmanned Air Vehicle (UAV) has attracted attention in recent years in conducting missions for longer time with higher levels of autonomy. For the enhanced autonomous characteristic of UAV, path planning is one of the crucial issues. Current researches on the graph search algorithms under combinatorial method are mainly reviewed in this paper by keeping focus on the comprehensive surveys of its properties for path planning. The outcome is a pen picture of their assumptions and drawbacks.

Journal ArticleDOI
TL;DR: In this article, a modified Sine Cosine Algorithm (M-SCA) is proposed to improve the controller parameter of an array of turbines such that the total energy production of wind plant is increased.
Abstract: This paper presents a Modified Sine Cosine Algorithm (M-SCA) to improve the controller parameter of an array of turbines such that the total energy production of wind plant is increased. The two modifications employed to the original SCA are in terms of the updated step size gain and the updated design variable equation. Those modifications are expected to enhance the variation of exploration and exploitation rates while avoiding the premature convergence condition. The effectiveness of the M-SCA is applied to maximize energy production of a row of ten turbines. The statistical performance analysis shows that the M-SCA provides the highest total energy production as compared to other existing methods.

Journal ArticleDOI
TL;DR: The proposed of integration of WDM and RoF-OFDM system is to achieve 100 km fiber length using 4QAM sequence bit, and the received power with electrical and optical amplifications by using 10 Gbps data signal.
Abstract: The optical communication and wireless networks can be integrated to increase the capacity and mobility with decrease the costs in the access networks. Optical communication is considered a Fiber optic communication that can be used for wired and wireless communication. The problems of Fiber optic communication have a solution represented by Radio over fiber (RoF) which can control many base stations (BSs) that connect to a central station (CS) with an optical fiber. The Coherent optical OFDM (CO-OFDM) have concerned a great interest due to the high spectral efficiency and strength to the fiber dispersion, also it can be considered as a promising candidate when used in long haul optical fiber transmission systems. The integration of the wavelength division multiplexing system (WDM) with (CO-OFDM) system for increasing the system performance as well as achieving high data rates. The simulation of WDM-ROF and (WDM-CO-OFDM) with an optisystem simulator to analyze the RF spectrum, spectrum signal visualizers, and constellation diagrams. The proposed of integration of WDM and RoF-OFDM system is to achieve 100 km fiber length using 4QAM sequence bit, and the received power with electrical and optical amplifications by using 10 Gbps data signal.

Journal ArticleDOI
TL;DR: This project aims to solve problems with current crowdfunding scene by applying Ethereum smart contracts to the crowdfunding site to that the contracts will be fully automatically executed, thus preventing frauds and ensuring that the projects can be delivered within duration given.
Abstract: Initially, blockchain is only used as a foundation of cryptocurrency, but today, we can see the rise of this new emerging technology are being implemented in many industries. In the future, most technologies around the world are expected to use blockchain as an efficient way to make online transactions. One of the areas that blockchain technologies can be applied is crowdfunding platforms. The most common problem with current crowdfunding scene in around the world including is that the campaigns are not regulated and some of the crowd-funding campaign turned out to be fraud. Besides, the completion of some projects also was significantly delayed. This project aims to solve these problems by applying Ethereum smart contracts to the crowdfunding site to that the contracts will be fully automatically executed, thus preventing frauds and ensuring that the projects can be delivered within duration given.

Journal ArticleDOI
Sk. Hasane Ahammad1, V. Rajesh1, A. Neetha1, Sai Jeesmitha. B1, A. Srikanth1 
TL;DR: A novel stage explored turn reverberation dispersion weighted interleaved reverberation planar imaging arrangement in seven sound volunteers and six patients with intramedullary injuries to build up another examination strategy and try its unwavering quality and potential for adding to the symptomatic workup of patients with spinal rope indications.
Abstract: Dissemination weighted MR imaging may build the affectability and explicitness of MR imaging for certain pathologic states of the spinal rope yet is once in a while performed as a result of a few specialized issues. We consequently tried a novel stage explored turn reverberation dispersion weighted interleaved reverberation planar imaging arrangement in seven sound volunteers and six patients with intramedullary injuries. We performed dispersion weighted MR imaging of the spinal string with high spatial goals. Distinctive examples of dissemination irregularities saw in patient investigations bolster the conceivable symptomatic effect of dispersion weighted MR imaging for ailments of the spinal string. MR imaging has turned into the system of decision for imaging the spinal rope on account of a high affectability for pathologic intra medullary changes. In any case, the explicitness of anomalies oftentimes lingers behind when utilizing just regular MR arrangements. Dissemination weighted MR imaging guarantees to supply additional data in light of trademark changes of the clear dispersion coefficient, for example, those showed in intense ischemia, tumors, or sores related among numerous sclerosis. To date, the indicative commitment of dispersion weighted MR imaging has been concerted essentially in the cerebrum since dissemination weighted MR imaging of the spine is in detail every one the more requesting. Both the little size of the spinal rope and movement-initiated antiquities must be considered. We in this manner built up another examination strategy and tried its unwavering quality and potential for adding to the symptomatic workup of patients with spinal rope indications.

Journal ArticleDOI
TL;DR: In this paper, an attempt is being made to make use of the Image processing techniques, to study the frontal face features of college students and predict depression, which is trained with facial features of positive and negative facial emotions.
Abstract: Psychological problems in college students like depression, pessimism, eccentricity, anxiety etc. are caused principally due to the neglect of continuous monitoring of students’ psychological well-being. Identification of depression at college level is desirable so that it can be controlled by giving better counseling at the starting stage itself. The disturbed mental state of a student suffering from depression would be clearly evident in the student’s facial expressions.Identification of depression in large group of college students becomes a tedious task for an individual. But advances in the Image-Processing field have led to the development of effective systems, which prove capable of detecting emotions from facial images, in a much simpler way. Thus, we need an automated system that captures facial images of students and analyze them, for effective detection of depression. In the proposed system, an attempt is being made to make use of the Image processing techniques, to study the frontal face features of college students and predict depression. This automated system will be trained with facial features of positive and negative facial emotions. To predict depression, a video of the student is captured, from which the face of the student is extracted. Then using Gabor filters, the facial features are extracted. Classification of these facial features is done using SVM classifier. The level of depression is identified by calculating the amount of negative emotions present in the entire video. Based on the level of depression, notification is send to the class advisor, department counselor or university counselor, indicating the student’s disturbed mental state. The present system works with an accuracy of 64.38%. The paper concludes with the description of an extended architecture for depression detection as future work.

Journal ArticleDOI
TL;DR: In this paper, the authors have reported an effective implementation for Internet of Things used for monitoring the level of air pollution based on Malaysia Air Pollution Index (API) which is a low-cost and real time system would be able to monitor regular air quality pollutants including Particulate Matter (PM) of PM2.5, PM10 and Carbon Monoxide (CO) gas as well as the temperatures and humidity of the surroundings.
Abstract: The atmospheric air pollution is a major concern in modern cities, especially in developing countries like Malaysia. In this paper, we have reported an effective implementation for Internet of Things used for monitoring the level of air pollution based on Malaysia Air Pollution Index (API). The low-cost and real time system would be able to monitor regular air quality pollutants including Particulate Matter (PM) of PM2.5, PM10 and Carbon Monoxide (CO) gas as well as the temperatures and humidity of the surroundings. The system has capability to detect Good, Moderate, Unhealthy, Very Unhealthy and Hazardous API status. Based on 5 weeks of experimental API monitoring result on specified test location, the system was able to demonstrate promising results in providing a reliable real time monitoring of the air quality condition.

Journal ArticleDOI
TL;DR: A robust nonlinear control of active and reactive power with the use of the Backstepping and Sliding Mode Control approach based on a doubly fed Induction Generator power (DFIG-Generator) in order to reduce the response time of the wind system.
Abstract: This article, present a new contribution to the control of wind energy systems, a robust nonlinear control of active and reactive power with the use of the Backstepping and Sliding Mode Control approach based on a doubly fed Induction Generator power (DFIG-Generator) in order to reduce the response time of the wind system. In the first step, a control strategy of the MPPT for the extraction of the maximum power of the turbine generator is presented. Subsequently, the Backstepping control technique followed by the sliding mode applied to the wind systems will be presented. These two types of control system rely on the stability of the system using the LYAPUNOV technique. Simulation results show performance in terms of set point tracking, stability and robustness versus wind speed variation.

Journal ArticleDOI
TL;DR: This paper introduces a new construction of a novel 5- input majority gate and compares the proposed gate with the most important previous counterpart gates.
Abstract: Transistor-based CMOS technology has many drawbacks such as power consumption and cannot continue in following the scaling of Moore's law and system-on-a-chip in near future. These drawbacks lead the researchers to think about an alternative technology. Quantum-dot Cellular Automata (QCA) is a new nanoscale technology can implement the logical functionality by controlling the position of the electron. The basic building blocks for QCA circuit are majority gate and inverter. where AND and OR gate can be implemented using Majority gate by setting one of the inputs to "0" and "1" respectively. A lot of papers was introduced to propose a new gates construction such as XOR and 5- input majority gate in last few years. The complexity of the gate leads to the complexity of the whole circuit so whenever the proposed gate has a lower number of cells, that's mean it’s better. In this paper, we introduce a new construction of a novel 5- input majority gate. QCADesigner tool will be used to show the simulation result of the proposed gate. Then we will compare the proposed gate with the most important previous counterpart gates.

Journal ArticleDOI
TL;DR: In this article, a hexagonal shape patch with two folded capacitive loaded line Resonators (CLLRs) on the left edge of the patch antenna is used to implement UWB applications (3.1-10.6 GHz).
Abstract: In this paper, we proposed a hexagonal shaped microstrip ultra-wideband (UWB) antenna integrated with dual band applications. The antenna design consists of a hexagonal shape patch with two folded Capacitive Loaded Line Resonators (CLLRs) on the left edge of the patch antenna. This hexagonal structure is used to implement UWB applications (3.1-10.6 GHz). A rectangular ground , and two CLLR are also used on t he bottom of antenna to obtain the extra dual resonant frequency at 2.4 GHz and 9.1 GHz for B luetooth and radar applications respectively. The proposed design is implemented using FR4 epoxy substrate. The relative permittivity of the substrate is 4 .4. The overall size of designing antenna is 26 × 30 mm2 with 1.6 mm as thickness and fed by standard feed line of 50 Ω microstrip . The results obtained from the simulation indicate that the designed antenna attains a good bandwidth from 1.1 GHz – 10.69 GHz with VSWR < 2 and return loss < -10 dB. The proposed geometry is s imulated by using the Ansoft HFSS simulator working on the principle of FEM and results are also analyzed.

Journal ArticleDOI
TL;DR: CAPTCHA codes are embedded into cover image with an encrypted form resulting stego image and thus attackers cannot fetch the actual CAPTCHA resulting in a secured transmission of confidential data using image steganography.
Abstract: Steganography is data hiding technique in internet. Here we send CAPTCHA codes within a cover image using Image steganography. CAPTCHA are the crazy codes. They are used in human response test. The word is actually an acronym for: " C ompletely A utomated P ublic T uring test to tell C omputers and H umans A part". It is a type of challenge–response test used in computing to determine whether or not the user is a human. Websites implement CAPTCHA codes into their registration processes due to spam. This is the utility of CAPTCHA codes. Here we generate CAPTCHA codes and later send them in an encrypted version. So, actually CAPTCHA codes are embedded into cover image with an encrypted form resulting stego image and thus attackers cannot fetch the actual CAPTCHA resulting in a secured transmission of confidential data using image steganography.

Journal ArticleDOI
TL;DR: An improved cellular neural network (CNN) algorithm is proposed as the solution to detect the cancerous cells in real-time by undergoing the image processing of Pap smear images and can detect the cervix cancer cells automatically with more than 88% accuracy.
Abstract: Cervical cancer is the second most common in Malaysia and the fourth frequent cancer among women in worldwide. Pap smear test is often ignored although it is actually useful, beneficial and essential as screening tool for cervical cancer. However, Pap smear images have low sensitivity as well as specificity. Therefore, it is difficult to determine whether the abnormal cells are cancerous or not. Recently, computer-based algorithms are widely used in cervical cancer screening. In this study, an improved cellular neural network (CNN) algorithm is proposed as the solution to detect the cancerous cells in real-time by undergoing the image processing of Pap smear images. A few templates are combined and modified to form an ideal CNN algorithm to detect the cancerous cells in total of 115 Pap smear images. A MATLAB based CNN is developed for an automated detection of cervix cancerous cells where the templates segmented the nucleus of the cells. From the simulation results, our proposed CNN algorithm can detect the cervix cancer cells automatically with more than 88% accuracy.

Journal ArticleDOI
TL;DR: 3 boosting algorithms are proposed to build the classifier for predicting student’s performance and results indicate that it can build prediction model using one subject to predict another subject and build models from one subject dataset and test using onother subject dataset.
Abstract: Student’s performance is the most important value of the educational institutes for their competitiveness. In order to improve the value, they need to predict student’s performance, so they can give special treatment to the student that predicted as low performer. In this paper, we propose 3 boosting algorithms (C5.0, adaBoost.M1, and adaBoost.SAMME) to build the classifier for predicting student’s performance. This research used 1 UCI student performance datasets. There are 3 scenarios of evaluation, the first scenario was employ 10-fold cross-validation to compare performance of boosting algorithms. The result of first scenario showed that adaBoost.SAMME and adaBoost.M1 outperform baseline method in binary classification. The second scenario was used to evaluate boosting algorithms under different number of training data. On the second scenario, adaBoost.M1 was outperformed another boosting algorithms and baseline method on the binary classification. As third scenario, we build models from one subject dataset and test using onother subject dataset. The third scenario results indicate that it can build prediction model using one subject to predict another subject.