Showing papers in "Bulletin of Electrical Engineering and Informatics in 2019"
TL;DR: This paper wants to conduct experiment using supervised Machine Learning (ML) for network anomaly detection system that low communication cost and network bandwidth minimized by using UNSW-NB15 dataset to compare their performance in term of their accuracy (effective) and processing time (efficient) for a classifier to build a model.
Abstract: Network anomaly detection system enables to monitor computer network that behaves differently from the network protocol and it is many implemented in various domains. Yet, the problem arises where different application domains have different defining anomalies in their environment. These make a difficulty to choose the best algorithms that suit and fulfill the requirements of certain domains and it is not straightforward. Additionally, the issue of centralization that cause fatal destruction of network system when powerful malicious code injects in the system. Therefore, in this paper we want to conduct experiment using supervised Machine Learning (ML) for network anomaly detection system that low communication cost and network bandwidth minimized by using UNSW-NB15 dataset to compare their performance in term of their accuracy (effective) and processing time (efficient) for a classifier to build a model. Supervised machine learning taking account the important features by labelling it from the datasets. The best machine learning algorithm for network dataset is AODE with a comparable accuracy is 97.26% and time taken approximately 7 seconds. Also, distributed algorithm solves the issue of centralization with the accuracy and processing time still a considerable compared to a centralized algorithm even though a little drop of the accuracy and a bit longer time needed.
54 citations
TL;DR: This paper focuses on classification of motor imagery in Brain Computer Interface by using classifiers from machine learning technique and SVM, Logistic Regression and Naïve Bayes classifier achieved the highest accuracy with 89.09% in AUC measurement.
Abstract: This paper focuses on classification of motor imagery in Brain Computer Interface (BCI) by using classifiers from machine learning technique. The BCI system consists of two main steps which are feature extraction and classification. The Fast Fourier Transform (FFT) features is extracted from the electroencephalography (EEG) signals to transform the signals into frequency domain. Due to the high dimensionality of data resulting from the feature extraction stage, the Linear Discriminant Analysis (LDA) is used to minimize the number of dimension by finding the feature subspace that optimizes class separability. Five classifiers: Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Naive Bayes, Decision Tree and Logistic Regression are used in the study. The performance was tested by using Dataset 1 from BCI Competition IV which consists of imaginary hand and foot movement EEG data. As a result, SVM, Logistic Regression and Naive Bayes classifier achieved the highest accuracy with 89.09% in AUC measurement.
47 citations
TL;DR: The proposed defected ground structure-based microstrip patch antenna has been proposed that can work for narrowband applications and is light weighted, low cost, easy to fabricate and with better performances that makes it suitable for biomedical WLAN applications.
Abstract: Proper narrowband antenna design for wearable devices in the biomedical application is a significant field of research interest. In this work, defected ground structure-based microstrip patch antenna has been proposed that can work for narrowband applications. The proposed antenna works exactly for a single channel of ISM band. The resonant frequency of the antenna is 2.45 GHz with a return loss of around -30 dB. The -10dB impedance bandwidth of the antenna is 20 MHz (2.442-2.462 GHz), which is the bandwidth of channel 9 in ISM band. The antenna has achieved a high gain of 7.04 dBi with an increase of 17.63% antenna efficiency in terms of realized gain by using defected ground structure. Three linear vector arrays of arrangement 1 2, 1 4 and 1 8 have been designed to validate the proposed antenna performances as an array. The proposed antenna is light weighted, low cost, easy to fabricate and with better performances that makes it suitable for biomedical WLAN applications.
29 citations
TL;DR: An automated system that will automatically saves student’s attendance into the database using face recognition method will be presented, which will ensure that the attendance taking process will be faster and more accurate.
Abstract: Attendance is important for university students. However, generic way of taking attendance in universities may include various problems. Hence, a face recognition system for attendance taking is one way to combat the problem. This paper will present an automated system that will automatically saves student’s attendance into the database using face recognition method. The paper will elaborate on student attendance system, image processing, face detection and face recognition. The face detection part will be done by using viola-jones algorithm method while the face recognition part will be carried on by using local binary pattern (LBP) method. The system will ensure that the attendance taking process will be faster and more accurate.
27 citations
TL;DR: 10-channels of mode division multiplexer over hybrid free-space optics (FSO) link in several weather conditions to achieve the maximum possible medium range and fiber to the home (FTTH) for high bandwidth access networks is designed and investigated.
Abstract: In this paper, we design and investigate 10-channels of mode division multiplexer (MDM) over hybrid free-space optics (FSO) link in several weather conditions to achieve the maximum possible medium range and fiber to the home (FTTH) for high bandwidth access networks. System capacity can be effectively increased with the use of MDM over hybrid FSO-FTTH. In this study, a 10-channel MDM over FSO-FTTH system has been analyzed in different weather conditions that operate at 1550 nm wavelength. The simulated system has transmitted 100 Gbit/s up for a distance of 3200 meters FSO in superbly clear weather condition. It also transmitted 100 Gbit/s up for a distance of 650 meters FSO during heavy rain. The validation of this study is measures based on eye diagrams bit-error rates (BER) that have been analyzed.
22 citations
TL;DR: The objective of this paper is to predict the diagnosis of CKD based on the symptoms or attributes observed in a particular case, whether the stage is acute or chronic, and it showed that the regression classifier perform best in the kidney diagnostic procedure.
Abstract: Chronic Kidney Disease (CKD) is one of the leading cause of death contributed by other illnesses such as diabetes, hypertension, lupus, anemia or weak bones that lead to bone fractures. Early prediction of CKD is important in order to contain the disesase. However, instead of predicting the severity of CKD, the objective of this paper is to predict the diagnosis of CKD based on the symptoms or attributes observed in a particular case, whether the stage is acute or chronic. To achieve this, a classification model is proposed to label stage of severity for kidney diseases patients. The experiments then investigated the performance of the proposed classification model based on eight supervised classification algorithms, which are ZeroR, Rule Induction, Support Vector Machine, Naive Bayes, Decision Tree, Decision Stump, k-Nearest Neighbour, and Classification via Regression. The performance of the all classifiers is evaluated based on accuracy, precision, and recall. The results showed that the regression classifier perform best in the kidney diagnostic procedure.
22 citations
TL;DR: Results illustrate that nonlinear DENFIS equalization scheme can improve the received distorted signal from an MDM with better accuracy than previous linear equalization schemes such as recursive‐least‐square (RLS) algorithm.
Abstract: The performance of optical mode division multiplexer (MDM) is affected by inter-symbol interference (ISI), which arises from higher-order mode coupling and modal dispersion in multimode fiber (MMF). Existing equalization algorithms in MDM can mitigate linear channel impairments, but cannot tackle nonlinear channel impairments accurately. Therefore, mitigating the noise in the received signal of MDM in the presence of ISI to recover the transmitted signal is important issue. This paper aims at controlling the broadening of the signal from MDM and minimizing the undesirable noise among channels. A dynamic evolving neural fuzzy inference system (DENFIS) equalization scheme has been used to achieve this objective. Results illustrate that nonlinear DENFIS equalization scheme can improve the received distorted signal from an MDM with better accuracy than previous linear equalization schemes such as recursive‐least‐square (RLS) algorithm. Desirably, this effect allows faster data transmission rate in MDM. Additionally, the successful offline implementation of DENFIS equalization in MDM encourages future online implementation of DENFIS equalization in embedded optical systems.
18 citations
TL;DR: This study focused on an algorithm that was thoroughly made and the methods in implementing this algorithm are discussed in detail, which can be used in the machine learning method to prevent phishing attacks.
Abstract: The development of computer networks today has increased rapidly. This can be seen based on the trend of computer users around the world, whereby they need to connect their computer to the Internet. This shows that the use of Internet networks is very important, whether for work purposes or access to social media accounts. However, in widely using this computer network, the privacy of computer users is in danger, especially for computer users who do not install security systems in their computer. This problem will allow hackers to hack and commit network attacks. This is very dangerous, especially for Internet users because hackers can steal confidential information such as bank login account or social media login account. The attacks that can be made include phishing attacks. The goal of this study is to review the types of phishing attacks and current methods used in preventing them. Based on the literature, the machine learning method is widely used to prevent phishing attacks. There are several algorithms that can be used in the machine learning method to prevent these attacks. This study focused on an algorithm that was thoroughly made and the methods in implementing this algorithm are discussed in detail.
18 citations
TL;DR: In this paper, the preparation of polystyrene-copper oxide (PS-CuO) nanocomposites for piezoelectric application was investigated and the results showed that the dielectric constant, dielectoric loss and A.C electrical conductivity increases with increase in frequency.
Abstract: The preparation of (polystyrene-copper oxide) nanocomposites have been investigated for piezoelectric application. The copper oxide nanoparticles were added to polystyrene by different concentrations are (0, 4, 8 and 12) wt.%. The structural and A.C electrical properties of (PS-CuO) nanocomposites were studied. The results showed that the dielectric constant and dielectric loss of (PS-CuO) nanocomposites decrease with increase in frequency. The A.C electrical conductivity increases with increase in frequency. The dielectric constant, dielectric loss and A.C electrical conductivity of polystyrene increase with increase in copper oxide nanoparticles concentrations. The results of piezoelectric application showed that the electrical resistance of (PS-CuO) nanocomposites decreases with increase in pressure.
17 citations
TL;DR: Water Quality Catchment Monitoring System was introduced to check and monitor water quality continuously and IMU is a new feature in the system where the direction of x and y is determined for planning and find out where a water quality problem exists by determining the flow of water.
Abstract: Water quality is the main aspect to determine the quality of aquatic systems. Poor water quality will pose a health risk for people and ecosystems. The old methods such as collecting samples of water manually and testing and analysing at lab will cause the time consuming, wastage of man power and not economical. A system is needed to provide a real-time data for environmental protection and tracking pollution sources. This paper aims to describe on how to monitor water quality continuously through IoT platform. Water Quality Catchment Monitoring System was introduced to check and monitor water quality continuously. It’s features five sensors which are temperature sensor, light intensity sensor, pH sensor, GPS tracker and Inertia Movement Unit (IMU). IMU is a new feature in the system where the direction of x and y is determined for planning and find out where a water quality problem exists by determining the flow of water. The system uses an internet wireless connection using the ESP8266 Wi-Fi Shield Module as a connection between Arduino Mega2560 and laptop. ThingSpeak application acts as an IoT platform used for real-time data monitoring.
16 citations
TL;DR: A flood mitigation method will be evaluated which incorporates a miniaturized flow, water level sensor and pressure gauge which has the highest accuracy of 98.9% and precision of 100% when 2-class neural network is used.
Abstract: The number of natural disasters occurring yearly is increasing at an alarming rate which has caused a great concern over the well-being of human lives and economy sustenance. The rainfall pattern has also been affected and this has caused immense amount of flood cases in recent times. Flood disasters are damaging to economy and human lives. Yearly, millions of people are affected by floods in Asia alone. This has brought the attention of the government to develop a flood forecasting method to reduce flood casualties. In this article, a flood mitigation method will be evaluated which incorporates a miniaturized flow, water level sensor and pressure gauge. The data from the two sensors are used to predict flood status using a 2-class neural network. Real-time monitoring of the data from the sensor into Thingspeak channel were possible with the use of NodeMCU ESP8266. Furthermore, Microsoft’s Azure Machine Learning (AzureML) has built-in 2-class neural network which was used to predict flood status according to predefine rule. The prediction model has been published as Web services through AzureML service and it enables prediction as new data are available. The experimental result showed that using 3 hidden layers has the highest accuracy of 98.9% and precision of 100% when 2-class neural network is used.
TL;DR: The mobile application of AR book on the fall of Melaka Empire history has been developed successfully and the findings show that most users agree that the application contributes to higher users’ satisfaction.
Abstract: Augmented Reality (AR) is a technology that enables a new information delivery environment. AR promotes both engagement and motivation for people to obtain and acquire certain knowledge or information including those concerning history. People, especially the young generation, often view history as an uninteresting and boring subject matter. This may be due to the lack of interactivity and visual images that accompanying the information on history. This could affect our level of understanding about the history of our country such as the fall of Melaka Empire and weaken our spirit of patriotism. Thus, this research aims to study the effect of combining the AR technology together with the traditional information to create excitement in learning history. The development of the AR application in this project is to enhance the traditional book by allowing users to see the digital visual of historical events. The development of the application involves five phases that are analysis, design, develop, implement, and evaluate. The mobile application of AR book on the fall of Melaka Empire history has been developed successfully and the findings show that most users agree that the application contributes to higher users’ satisfaction.
TL;DR: In this paper, the authors presented a model and analysis of PV/Wind/Diesel hybrid system for rural electrification in Kaduna state, northern Nigeria, using HOMER (Hybrid Optimization Model for Electric Renewable) software tool.
Abstract: The scarce electricity supply in Nigeria is a key factor to the low industrial development in a country well-known for having the least electrification in Africa per capita. Presently, Nigeria employs four different kinds of energy such as coal, natural gas, hydro, and oil. Three of the four resources mentioned above used for the production of energy in Nigeria is connected with increasing emissions of greenhouse gas: natural gas, oil, and coal, with coal releasing the worst. This paper presents a model and analysis of PV/Wind/Diesel hybrid system for rural electrification in Kaduna state, northern Nigeria. HOMER (Hybrid Optimization Model for Electric Renewable) software tool was used for optimization and modeling of this work. Simulation results show that the PV/Wind/Diesel system with Battery storage is the most cost-effective system since it recorded considerable cost of energy and reduces CO 2 emissions significantly.
TL;DR: The full Bayesian approach to assess the predictive distribution of all classes using three classifiers; naive Bayes (NB), bayesian networks (BN), and tree augmented naive bayes (TAN) with three datasets; Breast cancer, breast cancer wisconsin, and breast tissue dataset is presented.
Abstract: The problem of imbalanced class distribution or small datasets is quite frequent in certain fields especially in medical domain. However, the classical Naive Bayes approach in dealing with uncertainties within medical datasets face with the difficulties in selecting prior distributions, whereby parameter estimation such as the maximum likelihood estimation (MLE) and maximum a posteriori (MAP) often hurt the accuracy of predictions. This paper presents the full Bayesian approach to assess the predictive distribution of all classes using three classifiers; naive bayes (NB), bayesian networks (BN), and tree augmented naive bayes (TAN) with three datasets; Breast cancer, breast cancer wisconsin, and breast tissue dataset. Next, the prediction accuracies of bayesian approaches are also compared with three standard machine learning algorithms from the literature; K-nearest neighbor (K-NN), support vector machine (SVM), and decision tree (DT). The results showed that the best performance was the bayesian networks (BN) algorithm with accuracy of 97.281%. The results are hoped to provide as base comparison for further research on breast cancer detection. All experiments are conducted in WEKA data mining tool.
TL;DR: A measurement was conducted to study electromagnetic fields (EMF) radiation level in Pulau Pinang and the measurement is compared with the international standard provided by International Commission of Non-Ionizing Radiation Protection (ICNIRP).
Abstract: The residence of Pulau Pinang and Malaysia generally are worried with the possible health effects due to Base Tower Station (BTS) radiation. Particularly, the residents of Pulau Pinang are utilizing their mobile phones for multiple kind of tasks including communications, browsing the internet and other applications. With the recent advances in mobile communication technologies, the end user demanded a better coverage, great communication services, and faster speed for internet browsing. To fulfill the demand, service provider and communication companies are providing plenty of communication base tower leading to the beliefs of that the tower emitted radiation and cause harmful effect to human health and voiced out and complain to the municipal councils in Malaysia. In this paper, a measurement was conducted to study electromagnetic fields (EMF) radiation level in Pulau Pinang. The measurement is compared with the international standard provided by International Commission of Non-Ionizing Radiation Protection (ICNIRP). Far field measurement of different values of long term evolution (LTE) exposure was demonstrated in radiofrequency (RF) shielded environment. LTE850, LTE1800 and LTE2600 field exposure was compared in term of its’ electrical field and power density that adhere to the standard provided by ICNIRP.
TL;DR: In this paper, the authors proposed a high gain dielectric resonator antenna for 5G applications, which achieved a wide impedance bandwidth of 17.3% (23.8-28.3GHz=4.5 GHz) for S11-10 dB, and a maximum gain of about 9.3 dBi with radiation efficiency of 96% at design frequency of 26 GHz.
Abstract: In this paper, wideband high gain dielectric resonator antenna for 5G applications is presented. Higher order mode is exploited to enhance the antenna gain, while the array of symmetrical cylindrical shaped holes drilled in the DRA to improves the bandwidth by reducing the quality factor. The proposed DRA is designed using dielectric material with relative permittivity of 10 and loss tangent of 0. 002.The Rogers RT/Droid 5880 has been selected as substrate with relative permittivity of 2.2, loss tangent of 0.0009- and 0.254-mm thickness. The simulated results show that, the proposed geometry has achieved a wide impedance bandwidth of 17.3% (23.8-28.3GHz=4.5 GHz) for S11<-10 dB, and a maximum gain of about 9.3 dBi with radiation efficiency of 96% at design frequency of 26 GHz. The DRA is feed by microstrip transmission line with slot aperture. The reflection coefficient, the radiation pattern, and the antenna gain are studied by full-wave EM simulator CST Microwave Studio. The proposed antenna can be used for the 5G communication applications such as device to device communication (D2D).
TL;DR: The proposed Maximum Power Point Tracking Algorithm based on the incremental conductance variable step shows good performances in terms of efficiency and tracking speed.
Abstract: In this papier, a low-cost solar photovoltaic water pumping system based on an induction motor without the use of chemical energy storage is presented. In literature, we can find several Maximum Power Point Tracking Algorithms, the choice of the algorithm is according to the nature of application. In this article, Variable Step Size Incremental Conductance MPPT method has been developed since it is fast and has less oscillations. The studied photovoltaic pumping system contains a centrifugal pump which is driven by a three-phase asynchronous motor. To control the water flow, the field-oriented control has been implemented. The control system is applied on two cities with different climatic conditions to evaluate their performance. The photovoltaic pumping system is developed using the MATLAB/Simulink software to discuss the results obtained. Consequently, the proposed MPPT based on the incremental conductance variable step shows good performances in terms of efficiency and tracking speed.
TL;DR: In this study, WOA is developed to identify the optimal sizing of FACTS device for loss minimization in the power system and IEEE 30-bus RTS was used as the test system to validate the effectiveness of the proposed algorithm.
Abstract: As the world is progressing forward, the load demand in the power system has been continuously increasing day by day. This situation has forced the power system to operate under stress condition due to its limitation. Therefore, due to the stressed condition, the transmission losses faced higher increment with a lower minimum voltage. Theoretically, the installation of the Flexible AC Transmission System (FACTS) device can solve the problem experienced by the power system. This paper presents the Whale Optimization Algorithm for loss minimization using FACTS devices in the transmission system. Thyristor controlled series compensator (TCSC) is chosen for this study. In this study, WOA is developed to identify the optimal sizing of FACTS device for loss minimization in the power system. IEEE 30-bus RTS was used as the test system to validate the effectiveness of the proposed algorithm.
TL;DR: A novel approach of ant colony optimization (ACO) algorithm for discovering the optimum route for information transmission in the WSNs is proposed here for optimization and enhancement and an optimal route and best cost from the originating node to the target node can be detected.
Abstract: The methods to achieve efficient routing in energy constrained wireless sensor networks (WSNs) is a fundamental issue in networking research. A novel approach of ant colony optimization (ACO) algorithm for discovering the optimum route for information transmission in the WSNs is proposed here for optimization and enhancement. The issue of path selection to reach the nodes and vital correspondence parameters, for example, the versatility of nodes, their constrained vitality, the node residual energy and route length are considered since the communications parameters and imperatives must be taken into account by the imperative systems that mediate in the correspondence procedure, and the focal points of the subterranean insect framework have been utilized furthermore. Utilizing the novel technique and considering both the node mobility and the existing energy of the nodes, an optimal route and best cost from the originating node to the target node can be detected. The proposed algorithm has been simulated and verified using MATLAB and the simulation results demonstrate that new ACO based algorithm achieved improved performance, about 30% improvement compared with the traditional ACO algorithm, and faster convergence to determine the best cost route, and recorded an improvement in the energy consumption of the nodes per transmission.
TL;DR: With this control strategy the balanced grid current is obtained keeping THD values with in the specified range of IEEE-519 standard.
Abstract: In this paper a control scheme for three phase seven level cascaded H-bridge inverter for grid tied PV system is presented. As power generation from PV depends on varing environmental conditions, for extractraction of maximum power from PV array, fuzzy MPPT controller is incorporated with each PV array. It gives fast and accurate response. To maintain the grid current sinusoidal under varying conditions, a digital PI controller scheme is adopted. A MATLAB/Simulink model is developed for this purpose and results are presented. At last THD analysis is carried out in order to validate the performance of the overall system. As discussed, with this control strategy the balanced grid current is obtained keeping THD values with in the specified range of IEEE-519 standard.
TL;DR: There is a wide relationship between audio and image steganography techniques in their implementation form and LSB is one of the weakest techniques, but the safest and the most robust technique within each type of the presented medium.
Abstract: The present work carries out a descriptive analysis of the main steganography techniques used in specific digital media such as audio and image files. For this purpose, a literary review of the domains, methods, and techniques as part of this set was carried out and their functioning, qualities, and weaknesses are identified. Hence, it is concluded that there is a wide relationship between audio and image steganography techniques in their implementation form. Nevertheless, it is determined that LSB is one of the weakest techniques, but the safest and the most robust technique within each type of the presented medium.
TL;DR: The focus of this project is to design a system of street lights controller to provide a reduction in power consumption and the prototype was designed by using Light Dependent Resistor, Infrared sensor, battery, battery and LED.
Abstract: Smart street light is an intelligent control of street lights to optimize the problem of power consumption of the street, late in night. Conventional street lights are being replaced by Light Emitting Diode (LED) street lighting system, which reduces the power consumption. The focus of this project is to design a system of street lights controller to provide a reduction in power consumption. The prototype was designed by using Light Dependent Resistor (LDR), Infrared sensor (IR), battery and LED. The brightness of the lamps is being controlled in this project to reduce the power consumption. The dimming of the lamps depends on the speed of object motion detected such as pedestrians, cyclists and cars. The higher speed of moving object, the greater the level of intensity. For this idea, the innovation of street lights is not quite the same as conventional street lights that are controlled by timer switch or light sensor which automatically turns light on during sunset and off during sunrise. According to the study, motion detection devices may help to save up to 40% of energy per month.
TL;DR: In this study, the chromosome representation and the fitness function of GA is carefully designed to cater for a single load logistics robotic task and it turns out the proposed GA algorithms outperform the greedy algorithm by 40% to 80% improvement.
Abstract: The demand for autonomous logistics service robots requires an efficient task scheduling system in order to optimise cost and time for the robot to complete its tasks. This paper presents a Genetic algorithm (GA) based task scheduling system for a ground mobile robot that is able to find a global near-optimal travelling path to complete a logistics task of pick-and-deliver items at various locations. In this study, the chromosome representation and the fitness function of GA is carefully designed to cater for a single load logistics robotic task. Two variants of GA crossover are adopted to enhance the performance of the proposed algorithm. The performance of the scheduling is compared and analysed between the proposed GA algorithms and a conventional greedy algorithm in a virtual map and a real map environments that turns out the proposed GA algorithms outperform the greedy algorithm by 40% to 80% improvement.
TL;DR: In this article, a brief analysis of rain fading was presented based on the simultaneous measurement of one-minute rain rate and its effects on a short-terrestrial millimetre-wave point-to-point radio links.
Abstract: The main objective of this paper to determine multipath and time-varying channel behaviour of short-terrestrial millimetre-wave point-to-point radio links. In an attempt to invigorate the impact of rain attenuation on mm-wave channel parameters such as the RMS delay spread, path loss received power strength and Rician distribution with a K factor. A brief analysis of rain fading was presented based on the simultaneous measurement of one-minute rain rate and its effects on a short experimental link of 38 GHz. Rain fade average is observed as high as 16 dB for 300 m path at about 125 mm/hr rain intensity. The statistical spatial channel mode (SSCM) simulation software was utilized for an operating frequency of 38 GHz. To generate of power delay profile (PDP). For both omnidirectional and directional antenna. The RMS delay spread and path loss has been estimated using the environmental parameters of Kuala Lumpur city which illustrates the theoretical performances of 5G in Malaysia. It is observed that RMS delay spread, path loss received power strength and K factor effected dramatically by rain fade. (SSCM) simulation software has to be modified to consider rain fade dynamic characteristics to achieve ultra-reliability requirements of outdoor applications in the tropical regions. This study is important for understanding signal propagation phenomena in short distance and enabling the utilization of the millimetre wave band for an urban micro-cellular environment for 5G communication system.
TL;DR: The results presented emphasize that a satisfactory trajectory tracking precision and stability could be achieved using SOM Neural networking combination with PID and Fuzzy-PD controller.
Abstract: Robots can be mathematically modeled with computer programs where the results can be displayed visually, so it can be used to determine the input, gain, attenuate and error parameters of the control system. In addition to the robot motion control system, to achieve the target points should need a research to get the best trajectory, so the movement of robots can be more efficient. One method that can be used to get the best path is the SOM (Self Organizing Maps) neural network. This research proposes the usage of SOM in combination with PID and Fuzzy-PD control for finding an optimal path between source and destination. SOM Neural network process is able to guide the robot manipulator through the target points. The results presented emphasize that a satisfactory trajectory tracking precision and stability could be achieved using SOM Neural networking combination with PID and Fuzzy-PD controller.The obtained average error to reach the target point when using Fuzzy-PD=2.225% and when using PID=1.965%.
TL;DR: The system that this work worked on functions by recognizing vein patterns from images of fingers which are captured using near Infrared(NIR) technology and several experimental results are shown with training accuracy, training loss, Receiver Operating Characteristic (ROC) Curve and Area Under the Curve (AUC).
Abstract: In current biometric security systems using images for security authentication, finger vein-based systems are getting special attention in particular attributable to the facts such as insurance of data confidentiality and higher accuracy. Previous studies were mostly based on finger-print, palm vein etc. however, due to being more secure than fingerprint system and due to the fact that each person's finger vein is different from others finger vein are impossible to use to do forgery as veins reside under the skin. The system that we worked on functions by recognizing vein patterns from images of fingers which are captured using near Infrared(NIR) technology. Due to the lack of an available database, we created and used our own dataset which was pre-trained using transfer learning of AlexNet model and verification is done by applying correct as well as incorrect test images. The result of deep convolutional neural network (CNN) based several experimental results are shown with training accuracy, training loss, Receiver Operating Characteristic (ROC) Curve and Area Under the Curve (AUC).
TL;DR: The development of an Internet of Things (IoT) enabled device that can communicate with different digital energy meters through modbus protocol is presented and enables the campus-wide energy usage to be monitored and stored efficiently and economically as opposed to the capital-intensive SCADA system.
Abstract: Electricity bill is one of the major operating expenses in most of the commercial buildings and industrial plants. Thus, the buildings’ energy management system is an essential element that should be utilized to optimize the energy usage and hence, contributes to carbon footprint reduction. To achieve this, one needs to first understand how the energy is being used in the buildings before any saving measures can be identified and proposed. Therefore, this paper presents the development of an Internet of Things (IoT) enabled device that can communicate with different digital energy meters through modbus protocol. The prototype has been successfully installed in three locations in the main campus of Universiti Teknikal Malaysia Melaka (UTeM). The proposed solution enables the campus-wide energy usage to be monitored and stored efficiently and economically as opposed to the capital-intensive SCADA system.
TL;DR: In this article, the authors presented the development work for integrating an Internet of Things (IoT) with a fibrous capillary irrigation system based on the climatic demand estimated by the weather condition.
Abstract: This paper presents the development work for integrating an Internet of Things (IoT) with a fibrous capillary irrigation system based on the climatic demand estimated by the weather condition. The monitoring and control using an IoT system is critical for such application that is targeted for precision irrigation. The fibrous capillary irrigation system is managed by manipulating a water supply depth using the potential evapotranspiration (ETo). A soil mositure sensor was used to monitor the progress of the root water uptake and input the fuzzy logic system, to determine the water requirements for the crop medium. Experiment was conducted by using a Choy sum plant as the test crop grown in a greenhouse. The monitoring of the demand and management of the watering system was successful. The ETo data was able to approximate the crop water requirement in near real time.
TL;DR: The finding of the result shows, MMG signal of adjacent muscle can affect the classification accuracy of the classifier.
Abstract: Surface Mechanomyography (MMG) is the recording of mechanical activity of muscle tissue. MMG measures the mechanical signal (vibration of muscle) that generated from the muscles during contraction or relaxation action. It is widely used in various fields such as medical diagnosis, rehabilitation purpose and engineering applications. The main purpose of this research is to identify the hand gesture movement via VMG sensor (TSD250A) and classify them using Linear Discriminant Analysis (LDA). There are four channels MMG signal placed into adjacent muscles which PL-FCU and ED-ECU. The features used to feed the classifier to determine accuracy are mean absolute value, standard deviation, variance and root mean square. Most of subjects gave similar range of MMG signal of extraction values because of the adjacent muscle. The average accuracy of LDA is approximately 87.50% for the eight subjects. The finding of the result shows, MMG signal of adjacent muscle can affect the classification accuracy of the classifier.
TL;DR: In this article, an artificial magnetic conductor (AMCMC) structure was used to enhance the gain of the double microstrip patch antenna, which is intended to operate at 16 GHz where the prospect fifth generation (5G) spectrum might be located.
Abstract: The paper presents an artificial magnetic conductor (AMC) structure to enhance the gain of the double microstrip patch antenna. By placing this kind of metamaterial in between the two Rogers RT5880 substrates, the antenna achieved lots of improvement especially in terms of size miniaturization, bandwidth, return loss, gain and efficiency. The antenna is intended to operate at 16 GHz where the prospect fifth generation (5G) spectrum might be located. Integration of AMC structure into the proposed antenna helps to improve nearly 16.3% of gain and almost 23.6% of size reduction.