Proceeding of the Electrical Engineering Computer Science and Informatics
Not a member yet
649 research outputs found
Sort by
Emotion Recognition using Fisher Face-based Viola-Jones Algorithm
Get PDFIn the form of the image integral, this primitive feature accelerates the performance of the Viola-Jones algorithm. However, the robust feature is necessary to optimize the results of emotion recognition. Previous research [11] has shown that fisher face optimized projection matrix in the low dimensional features. This feature reduction approach is expected to balance time-consuming and accuracy. Thus we proposed emotion recognition using fisher face-based Viola-Jones Algorithm. In this study, PCA and LDA are extracted to get the fisher face value. Then fisher face is filtered using Cascading AdaBoost algorithm to obtain face area. In the facial area, the Cascading AdaBoost algorithm re-employed to recognize emotions. We compared the performance of the original viola jones and fisher face-based viola jones using 50 images on the State University of Malang dataset by measuring the accuracy and time-consuming in the fps. The accuracy and time-consuming of the Viola-Jones algorithm reach 0.78 and 15 fps, whereas our proposed methods reach 0.82 and 1 fps. It can conclude that the fisher face-based viola-jones algorithm recognizes facial emotion as more accurate than the viola-jones algorithm
Active Fault Tolerance Control For Sensor Fault Problem in Wind Turbine Using SMO with LMI Approach
Get PDFIn this paper, we start to investigate the sensor fault problem in a Wind Turbine model with Fault Tolerant Control (FTC). FTC is used to allow the parameters of the controller to be reconfigured in accordance error information obtained online from sensors to improve the stability and overall performance of the system when an error occurs. The design is divided into two parts. The first part is designed Sliding Mode Observer (SMO) based Fault Detection Filter (FDF) to generate a residual signal to estimate fault. FDF is designed to maximize sensitivity fault. The second is a design output feedback control and Fault Compensation to guarantee the stability and performance system from disturbance by ignoring faults. Moreover, the function of fault compensation is to minimize effect fault of the system. The main contribution of this research is FTC proved to solve the sensor fault problem in a Wind Turbine model. The simulation showed the effectiveness of this method to estimate the fault and stabilized the system faster to a steady condition
Quasi Z-Source Inverter as MPPT on Renewable Energy using Grey Wolf Technique
Get PDFZ-Source Inverter (ZSI) is famous power converter who has capability to deal with voltage sags, improved power factor and wide voltage range of output. Quasi Z Source Inverter (QZSI) is the modern ZSI who has continuous current of input and can reduce stress of the passive component. This paper proposes simple boost QZSI circuit as Maximum Power Point Tracking (MPPT) using Grey Wolf Optimization (GWO) algorithm in photovoltaic system. Grey Wolf algorithm has been compared with the Perturb and Observed (P&O) technique for gaining the maximum power from the sun. Both techniques can get the optimum power of solar panel not only at constant sun light condition but also under varying irradiance levels. The value of average power obtained from GWO technique is greater than P&O. Although the value of solar radiation changes, the output voltage remains stable and both algorithms carry on obtaining optimal power of the sun
Automatic Estimation of Human Weight From Body Silhouette Using Multiple Linear Regression
Get PDFEstimating weight based on 2D image is advantageous especially for contactless and rapid measurement. Several researches used additional thermal camera or Kinect camera, required subjects to do front and side pose and manually extract body measures. This research propose an algorithm to estimate body weight automatically using 2D visual image where subject only do front pose. This research studied 4 features of body measures which are: (F1) height, and width of (F2) shoulder, (F3) abdomen/waist plus arm, (F4) feet. Each feature was simply subtracted based on body proportion where normal body has 8 equal segments. Shoulder is in 2nd segment, abdomen/waist is in 4th segment and feet is in the last segment. Multiple Linear Regression is used to determine weight estimation formula of all combination of 4 features, 15 in total. The highest significance R2 (0.80) and RMSE 2.68 Kg is given when using all 4 features in the estimation formula
The Recognition Of Semaphore Letter Code Using Haar Wavelet And Euclidean Function
Get PDFSemaphore are one way of communicating over long distances using the semaphore flags. In Indonesia semaphore is used in scout activities as a method to send information in the form of a sentence containing the message. Sending the semaphore letter code tends to be difficult. Based on the need to semaphore learning, this research proposes an algorithm with image processing as a way to correct the movement of the semaphore letter code based on the image obtained by using the webcam. Digital image processing, Wavelet feature extraction, and Euclidean distance function are applied in this study to determine the best recognition rate of variation decimation and distance variation to sending semaphore letter code using the webcam. This study resulted in the best recognition rate of 95.4% in the 1 st decimation, recognition rate reached 94.6% in decimation 2, and recognition rate reached 94.2% in decimation 3. The result of the introduction of the semaphore letter code is on the introduction of movement as far as 3 to 5 meter
Measuring Knowledge Management Readiness of Indonesia Ministry of Trade
Get PDFKnowledge is one of the important assets for organization. Managing knowledge properly will enable the organization to achieve its objectives effectively and efficiently. Since risk of failed implementation of Knowledge Management (KM) might occur, organization needs to measure their KM Readiness beforehand to successfully implement KM. This study is intended to measure KM Readiness in government agency, namely Directorate of Bilateral Negotiations in Ministry of Trade. The research model for measuring KM readiness was developed based on previous relevant studies. KM enablers, individual acceptance, and KM SECI processes were used to develop the model and research instruments. KM Readiness in government agency was measured by accommodating factor analysis in research model. Data were collected from 53 employees as valid samples. The result shows that KM Readiness level of the Directorate of Bilateral Negotiations in Ministry of Trade is "ready but needs a few improvement"
A Feature-Based Fragile Watermarking of Color Image for Secure E-Government Restoration
Get PDFthis research developed a method using fragile watermarking technique for color images to achieve secure e-government tamper detection with recovery capability. Before performing the watermark insertion process, the RGB image is converted first into YCbCr image. The watermark component is selected from the image feature that approximates the original image, in which the chrominance value features as a watermark component. For a better detection process, 3-tuple watermark, check bits, parity bits, and recovery bits are selected. The average block in each 2 x 2 pixels is selected as 8 restoration bits of each component, the embedding process work on the pixels by modifying the pixels value of three Least Significant Bit (LSB) . The secret key for secure tamper detection and recovery, transmitted along with the watermarked image, and the algorithm mixture is used to extract information at the receiving end. The results show remarkably effective to restore tampered image
Analysis and Design of Decision Support System Dashboard for Predicting Student Graduation Time
Get PDFInformation Systems is one of the existing study program at Telkom University that has produced many graduates since it was established in 2008. However, not all graduates produced successfully completed the study period during the four years of normal study. The percentage of graduates on time has some decline between the target and the achievement of the study program. From academic year 2014/2015 to 2016/2017 decrease annually about 1% every year, which is it becomes problems for the credibility and existence of study program and also for academic planners who may have an impact on accreditation assessment process of the study program when it is audited. One of the efforts that can be done by the study program to increase the students on time graduation rate is by making decision support system dashboard that giving early warning to the lecturer or the head of the study program if there are students who are predicted not to graduate on time. By using the C4.5 algorithm to perform the data analysis by looking at the causes of student's graduation time and pureshare methodology to perform dashboard development method. The result of this study is a prototype of decision support system dashboard, because there are lack of analysis in decision making and the dashboard only showing information and temporary prediction. The data model that used on this research is labeling data that has been processed using C4.5 algorithm and data that has been through data cleansing process using Pentaho Data Integration. This prototype is expected to be used as a reference base to support academic planners in order to make this application run with real time data
Monitoring The Usage of Marine Fuel Oil Aboard Ketapang Gilimanuk Ship
Get PDFThe development of the shipping industry in Indonesia has continued to increase over the past 10 years due to the sabotage principle. This development can be seen from the increasing number of national vessels. The number of national vessels becomes wider from 6,041 units in 2005 to 24,046 units in 2016. The number of vessels makes monitoring the operational performance of the vessel difficult because each ship has different travel routes. This research made tools that can monitor the performance of ships especially the use of MFO aboard the ship. The sensors used to measure the volume of MFO in the tank on board are HC-SR04 ultrasonic sensors and potentiometer pendulum sensors. The data from the sensor was processed by Arduino Uno microcontroller. This study would compare the performance of ultrasonic sensors and potentiometer pendulum sensors mounted on MFO oil premises. The study was conducted by measuring the position of the ship horizontally, right and left tilted with a slope level of 30 degrees and 45 degrees. The result of this research is that the potentiometer pendulum sensor was better when MFO surface condition was flat with the average of error sensor 1.60%, while HC-SR04 ultrasonic sensor has an average of error for 2.87%. However, on the skewed surface conditions of MFO, the usage of HC - SR04 ultrasonic sensors was better with average of error for 3.21%, while the potentiometer pendulum sensor had an average of error for 8.66%
FVEC feature and Machine Learning Approach for Indonesian Opinion Mining on YouTube Comments
Get PDFMining opinions from Indonesian comments from YouTube videos are required to extract interesting patterns and valuable information from consumer feedback. Opinions can consist of a combination of sentiments and topics from comments. The features considered in the mining of opinion become one of the important keys to getting a quality opinion. This paper proposes to utilize FVEC and TF-IDF features to represent the comments. In addition, two popular machine learning approaches in the field of opinion mining, i.e., SVM and CNN, are explored separately to extract opinions in Indonesian comments of YouTube videos. The experimental results show that the use of FVEC features on SVM and CNN achieves a very significant effect on the quality of opinions obtained, in term of accuracy