Indonesian Journal of Electrical Engineering and Informatics (IJEEI)
Not a member yet
776 research outputs found
Sort by
Persian Text Classification using naive Bayes algorithms and Support Vector Machine algorithm
Get PDFOne of the several benefits of text classification is to automatically assign document in predefined category is one of the primary steps toward knowledge extraction from the raw textual data. In such tasks, words are dealt with as a set of features. Due to high dimensionality and sparseness of feature vector results from traditional feature selection methods, most of the proposed text classification methods for this purpose lack performance and accuracy. Many algorithms have been implemented to the problem of Automatic Text Categorization that’s why, we tried to use new methods like Information Extraction, Natural Language Processing, and Machine Learning. This paper proposes an innovative approach to improve the classification performance of the Persian text. Naive Bayes classifiers which are widely used for text classification in machine learning are based on the conditional probability. we have compared the Gaussian, Multinomial and Bernoulli methods of naive Bayes algorithms with SVM algorithm. for statistical text representation, TF and TF-IDF and character-level 3 (3-Gram) [6,9] were used. Finally, experimental results on 10 newsgroups
Research of the Sensitivity of the Quantized Coefficients of a Digital Bandpass Filters with Frequency Sampling
Get PDFThe article is devoted to the applied research of the dependence of the influence of the transfer function quantized coefficients of digital bandpass filters with frequency sampling on its attenuation characteristic. It is shown that only the coefficients, which depend on the frequency, when quantized, significantly distort the shape of the attenuation characteristic. Such coefficients in the article are called frequency coefficients. The magnitudes of the deviations of the quantized frequency coefficients from the calculated values at different values of the bit depth are analyzed. The attenuation characteristics of the digital comb of bandpass filters based on frequency sampling with calculated and quantized coefficients are analyzed. Practical recommendations are offered to minimize the influence of frequency coefficients quantization errors at the stage of solving the task of approximation of digital bandpass filters with frequency sampling. The result will be an optimal choice of the minimum number bit of the processors or programmable logic integrated circuits (FPGA), to be used for the implementation of digital bandpass filters with frequency sampling
Experimental Analysis on Double Layer Kapton Material using Peltier Thermoelectric Device
Get PDFKapton is one of the flexible materials used in the development of microwave components for the telecommunications system. The electrical properties of Kapton are dependent on the material's temperature. In this study, this material will be heated, and the electrical properties of dielectric permittivity and loss tangent will be analyzed. This material heating process is done by using Peltier thermoelectric which is installed with Aluminium alloy. The 0 V up to 7 V DC voltage was supplied to the Peltier during the heating process. Then, the electrical properties of Kapton were measured by using a dielectric probe and vector network analyzer (VNA) at frequencies of 1 GHz to 9 GHz. The results obtained show the Kapton temperature was increased from 27oC to 41oC. Meanwhile, the dielectric permittivity also varied from 1.72 to 1.64 at the frequency of 5 GHz when 4 V was used. The maximum loss tangent value of 0.5 was observed when the maximum DC voltage of 7 V was applied. The knowledge of this experimental work can be used to design reconfigurable microwave components for smart system application
Self-adaptive fuzzy-PID controller for AGC study in deregulated Power System
Get PDFThe aim of this paper elucidates the AGC issues in a large scale interconnected power system incorporating HVDC link under the deregulated environment. The performance of the system is degraded under the influence of abrupt load change, and parameter variation. To perceive a reliable and quality power supply, secondary robust controllers are essential. A novel self-adaptive Fuzzy-PID controller is proposed to ameliorate the dynamic performance of both the conventional PID and Fuzzy-PID controller, employed in the restructured power system. In self-adaptive Fuzzy-PID controller unlike the Fuzzy-PID controller, the output scaling factors are tuned dynamically while the controller is functioning. These three controllers are designed by enumerating different gains and scaling factors, applying a budding nature-inspired algorithm known as Wild Goat Algorithm (WGA). The superior dynamic performance of frequency and tie-line power deviation under self-adaptive Fuzzy-PID controller in comparison to its' counterparts is investigated by dispatching the scheduled and unscheduled power under different contracts such as poolco based transaction, bilateral transaction and contract violation based transaction through different tie-lines. The dynamic response under parameter variation and random load perturbation confers the robustness of the proposed controller
Wi-Fi For Indoor Device Free Passive Localization (DfPL): An Overview
Get PDFThe world is moving towards an interconnected and intercommunicable network of animate and inanimate objects with the emergence of Internet of Things (IoT) concept which is expected to have 50 billion connected devices by 2020. The wireless communication enabled devices play a major role in the realization of IoT. In Malaysia, home and business Internet Service Providers (ISP) bundle Wi-Fi modems working in 2.4 GHz Industrial, Scientific and Medical (ISM) radio band with their internet services. This makes Wi-Fi the most eligible protocol to serve as a local as well as internet data link for the IoT devices. Besides serving as a data link, human entity presence and location information in a multipath rich indoor environment can be harvested by monitoring and processing the changes in the Wi-Fi Radio Frequency (RF) signals. This paper comprehensively discusses the initiation and evolution of Wi-Fi based Indoor Device free Passive Localization (DfPL) since the concept was first introduced by Youssef et al. in 2007. Alongside the overview, future directions of DfPL in line with ongoing evolution of Wi-Fi based IoT devices are briefly discussed in this paper
Frequency Control of Microgrid with Renewable Generation using PID Controller based Krill Herd
Get PDFThe main of this paper is to provide optimal control of a state microgrid system. The proposed configuration composes of renewable generation systems such as solar photovoltaic system and wind turbine generator with a Diesel Engine Generator and Fuel-Cell. An Aqua electrolyzer and other energy storage systems such as battery and flywheel are also used in the proposed microgrid. A standard PID (Proportional Integral Derivative) controller scheme is introduced whose its parameters are determined using different optimizations algorithm such as Algorithm Genetic, Particle Swarm Optimization, and Krill Herd algorithm for minimizing frequency and power deviations, in order to enhance the operation of this system. The PID controller gains are optimized by resolving an objective function. The simulation results are shown, and given that the Krill Herd algorithm improves the performance of the system in comparison with GA and PSO based on PID. The efficiency of the system is improved
Experimental Studies on the Reactive Thrust of the Mobile Robot of Arbitrary Orientation
Get PDFThe problem of creating mobile robots of arbitrary orientation in the technological space is to ensure reliable retention of robots on the surface of any orientation. Therefore, well-known experimental studies are mainly devoted to the creation of systems for coupling the robot to the surface along which it moves. The purpose of this study is to create a device for compensating the gravitational load of a mobile robot. The article contains the results of experimental testing of a fundamentally new approach to counteract the gravitational load of a mobile robot, namely, the expediency of equipping the robot with a source of reactive thrust of a non-chemical origin. A pneumatic generator of aerodynamic lift is proposed as such a source. Such a force partially compensates or completely overcomes the gravitational load, while not allowing the transformation of a mobile robot into an aircraft. The specified condition is necessary to perform contact power technological operations in the maintenance of various industrial facilities. In other words, the thrust force should not exceed the adhesion forces of the mobile robot to the displacement surface. As a research method, a full factorial experiment of the operation of a jet thrust generator was used, which is a new way to increase the reliability of holding the robot on an arbitrary surface. The article describes the methodology and description of the full factorial experiment with varying independent factors at two extreme levels. As a result, an experimental solution to the problem of finding the quasi-optimal values of the aerodynamic lifting force depending on the parameters of the jet thrust generator is obtained. As a result, the combination of a new robot design with the results of experimental studies confirms the feasibility of using a pneumatic jet thrust generator as a means of increasing the reliability of holding mobile robots on an arbitrary orientation surface in the technological space
Face Recognition based on CNN 2D-3D Reconstruction using Shape and Texture Vectors Combining
Get PDFThis study proposes a face recognition model using a combination of shape and texture vectors that are used to produce new face images on 2D-3D reconstruction images. The reconstruction process to produce 3D face images is carried out using the convolutional neural network (CNN) method on 2D face images. Merging shapes and textures vector is used to produce correlation points on new face images that have similarities to the initial image used. Principal Component Analysis (PCA) is used as a feature extraction method, for the classification method we use the Mahalanobis method. The results of the tests can produce a better recognition rate compared to face recognition testing using 2D images
A LabVIEW Based Optimization and Integration of Supersonic Wind Tunnel Instrumentation System
No full textIndonesian National Institute of Aeronautics and Space have a supersonic wind tunnel for research in high speed object . The condition of LAPAN's supersonic wind tunnel can only be used for shockwave observation by using schlieren apparatus. The data acquisition system can not collect data from sting balance, some of the control panels are either not operational or it need calibration. Based from these conditions, this research is done to develop a new integrated control system and data acquisition so that the effectiveness of operation in terms of time and better data quality can be achieved. For angle of attack (AoA) control from manual operation, have been optimized to a digital control using PID control method. With the new system, the AoA control has been automated and a new testing option for moving the AoA while the wind tunnel running can be done. In terms of data acquisition, after the optimization it can collect better data, (noise / interference becomes smaller), and now it can record data from the balance, the pressure data, AoA position and block position can be recorded. The system was created using PXIe from National Instrument and LabVIEW graphical programming as user interface
Segmentation of Handwritten Chinese Character Strings Based on improved Algorithm Liu
No full textAlgorithm Liu attracts high attention because of its high accuracy in segmentation of Japanese postal address. But the disadvantages, such as complexity and difficult implementation of algorithm, etc. have an adverse effect on its popularization and application. In this paper, the author applies the principles of algorithm Liu to handwritten Chinese character segmentation according to the characteristics of the handwritten Chinese characters, based on deeply study on algorithm Liu.In the same time, the author put forward the judgment criterion of Segmentation block classification and adhering mode of the handwritten Chinese characters.In the process of segmentation, text images are seen as the sequence made up of Connected Components (CCs), while the connected components are made up of several horizontal itinerary set of black pixels in image. The author determines whether these parts will be merged into segmentation through analyzing connected components. And then the author does image segmentation through adhering mode based on the analysis of outline edges. Finally cut the text images into character segmentation. Experimental results show that the improved Algorithm Liu obtains high segmentation accuracy and produces a satisfactory segmentation result