EMITTER - International Journal of Engineering Technology
Not a member yet
261 research outputs found
Sort by
Stator Flux Estimator Using Feed-Forward Neural Network for Evaluating Hysteresis Loss Curve in Three Phase Induction Motor
Get PDFThe operation of induction motors with high performance contributes significantly to the global energy savings but hysteresis loss is one of the factors causing decreased performance. Stator flux density (B) and magnetic field intensity (H) must be plotted to know hysteresis loss quantity. Unfortunately, since the rotor rotates in time series, the stator flux density is unmeasurable quantities, it’s hard to direct sensored this properties because of limited airgap space and costly to install additional instrument. The purpose of this paper is to evaluate the hysteresis loss quantity in induction motor using a novel method of multilayer perceptron feed forward neural network as stator flux estimator and magnetizing current model as magnetic field intensity properties. This method is effective, because it’s non-destructive method, without an additional instrument, low cost, and suitable for real-time motor drive systems. The FFNN estimator response is satisfying because accurately estimate stator flux density for evaluating hysteresis loss quantity including its magnitude and phase angle. By using the proposed model, the stator flux density and magnetizing current can be plotted become hysteresis loss curve. The performance of flux response, speed response, torque response and error deviation of stator flux estimator has been presented, investigated, compared and verified in Simulink Matlab
Classification Algorithms of Maternal Risk Detection For Preeclampsia With Hypertension During Pregnancy Using Particle Swarm Optimization
Get PDFPreeclampsia is a pregnancy abnormality that develops after 20 weeks of pregnancy characterized by hypertension and proteinuria. Â The purpose of this research was to predict the risk of preeclampsia level in pregnant women during pregnancy process using Neural Network and Deep Learning algorithm, and compare the result of both algorithm. There are 17 parameters that taken from 1077 patient data in Haji General Hospital Surabaya and two hospitals in Makassar start on December 12th 2017 until February 12th 2018. We use particle swarm optimization (PSO) as the feature selection algorithm. This experiment shows that PSO can reduce the number of attributes from 17 to 7 attributes. Using LOO validation on the original data show that the result of Deep Learning has the accuracy of 95.12% and it give faster execution time by using the reduced dataset (eight-speed quicker than the original data performance). Beside that the accuracy of Deep Learning increased 0.56% become 95.68%. Generally, PSO gave the excellent result in the significantly lowering sum attribute as long as keep and improve method and precision although lowering computational period. Deep Learning enables end-to-end framework, and only need input and output without require for tweaking the attributes or features and does not require a long time and complex systems and understanding of the deep data on computing
Simulation of Water Allocation Optimization Problem
Get PDFPollution prevention is primarily stimulated by economics, legislation, liability concerns, and the enhanced environmental benefit of managing waste at source. Chemical process industries consume a huge amount of water. Consequently, wastewater streams from such industries which contain various contaminants may create environmental problem. The increasing cost of fresh water supply and wastewater treatment has encouraged process industries to minimize fresh water consumption and waste water generation. This paper presents a formulation of water allocation problem (WAP) in order to minimize fresh water consumption in multi contaminant mass exchanger network. The approach is based on mass balance equation within the system being studied. The problem were then solved by using Matlab Optimization Toolbox
Adaptive Modulation and Coding (AMC) around Building Environment for MS Communication at The Train
Get PDFThis paper focused at communication systems when train moved. The communication propagation was influenced by building environment. The communication condition that used uplink direction. Mobile station was placed inside the train where moved with 500 km/hour velocity. The analysis was used consists of Doppler effect, atmospheric, and building environment. The variation communication frequency was used consists of 2.6 GHz, 5 GHz, and 10 GHz. Diffraction mechanism caused building was used single knife edge method. The result was showed SNR value from the communication frequency variation, distance comparison between LOS and NLOS, alteration adaptive modulation and coding (AMC), and coverage area percentage. Modulation and Coding Scheme (MCS) was used for AMC consists of QPSK, 16 QAM, and 64 QAM. Decreases of SNR value can be occured when communication distance for NLOS condition farther then LOS condition. That distance became increases because was obstructed with high building. Changeable of AMC value was caused propagation condition. The coverage area percentage when communication frequency that was used consists of 2.6 GHz, 5 GHz, and 10 GHz was obtained 88.4%, 88.4%, and 81.7%
A Time-Series Phrase Correlation Computing System With Acoustic Signal Processing For Music Media Creation
Get PDFThis paper presents a system that analyzes the time-series impression change in the acoustic signal by a unit of music phrase. The aim is to support the music creation using a computer (computer music) by bringing out composers' potentially existing knowledge and skills. Our goal is to realize the cross-genre/cross-cultural music creation. Our system realizes the automatic extraction of musical features from acoustic signals by dividing and decomposing them into “phrases†and “three musical elements†(rhythm, melody, and harmony), which are meaningful for human recognition. By calculating the correlation between the target “target music piece†and the “typical phrase†in each musical genre, composers are able to grasp the time-series impression change of music media by the unit of music phrase. The system leads to a new creative and efficient environment for cross-genre/cross-cultural music creation based on the potentially existing knowledge on the music phrase and structure
Javanese Character Feature Extraction Based on Shape Energy
Get PDFJavanese character is one of Indonesia's noble culture, especially in Java. However, the number of Javanese people who are able to read the letter has decreased so that there need to be conservation efforts in the form of a system that is able to recognize the characters. One solution to these problem lies in Optical Character Recognition (OCR) studies, where one of its heaviest points lies in feature extraction which is to distinguish each character. Shape Energy is one of feature extraction method with the basic idea of how the character can be distinguished simply through its skeleton. Based on the basic idea, then the development of feature extraction is done based on its components to produce an angular histogram with various variations of multiples angle. Furthermore, the performance test of this method and its basic method is performed in Javanese character dataset, which has been obtained from various images, is 240 data with 19 labels by using K-Nearest Neighbors as its classification method. Performance values were obtained based on the accuracy which is generated through the Cross-Validation process of 80.83% in the angular histogram with an angle of 20 degrees, 23% better than Shape Energy. In addition, other test results show that this method is able to recognize rotated character with the lowest performance value of 86% at 180-degree rotation and the highest performance value of 96.97% at 90-degree rotation. It can be concluded that this method is able to improve the performance of Shape Energy in the form of recognition of Javanese characters as well as robust to the rotation
Tooth Color Detection Using PCA and KNN Classifier Algorithm Based on Color Moment
Get PDFMatching the suitable color for tooth reconstruction is an important step that can make difficulties for the dentists due to the subjective factors of color selection. Accurate color matching system is mainly result based on images analyzing and processing techniques of recognition system.  This system consist of three parts, which are data collection from digital teeth color images, data preparation for taking color analysis technique and extracting the features, and data classification involve feature selection for reducing the features number of this system. The teeth images which is used in this research are 16 types of teeth that are taken from RSGM UNAIR SURABAYA. Feature extraction is taken by the characteristics of the RGB, HSV and LAB based on the color moment calculation such as mean, standard deviation, skewness, and kurtosis parameter. Due to many formed features from each color space, it is required addition method for reducing the number of features by choosing the essential information like Principal Component Analysis (PCA) method. Combining the PCA feature selection technique to the clasification process using K Nearest Neighbour (KNN) classifier algorithm can be improved the accuracy performance of this system. On the experiment result, it showed that only using KNN classifier achieve accuracy percentage up to 97.5 % in learning process and 92.5 % in testing process while combining PCA with KNN classifier can reduce the 36 features to the 26 features which can improve the accuracy percentage up to 98.54 % in learning process and  93.12% in testing process. Adding PCA as the feature selection method can be improved the accuracy performance of this color matching system with little number of features.Â
Application of Artificial Neural Networks in Modeling Direction Wheelchairs Using Neurosky Mindset Mobile (EEG) Device
Get PDFThe implementation of Artificial Neural Network in prediction the direction of electric wheelchair from brain signal input for physical mobility impairment.. The control of the wheelchair as an effort in improving disabled person life quality. The interaction from disabled person is helping in relation to social life with others. Because of the mobility impairment, the wheelchair with brain signal input is made. This wheel chair is purposed to help the disabled person and elderly for their daily activity. ANN helps to develop the mapping from input to target. ANN is developed in 3 level: input level, one hidden level, and output level (6-2-1). There are 6 signal from Neurosky Mindset sensor output, Alpha1, Alpha2, Raw signal, Total time signal, Attention Signal, and Meditation signal. The purpose of this research is to find out the output value from ANN: value in turning right, turning left, and forward. From those outputs, we can prove the relevance to the target. One of the main problem that interfering with success is the problem of proper neural network training. Arduino uno is chosen to implement the learning program algorithm because it is a popular microcontroller that is economic and efficient. The training of artificial neural network in this research uses 21 data package from raw data, Alpha1, Aplha2, Meditation data, Attention data, total time data. At the time of the test there is a value of Mean square Error(MSE) at the end of training amounted to 0.92495 at epoch 9958, value a correlation coefficient of 0.92804 shows that accuracy the results of the training process good.  Keywords: Navigation, Neural network, Real-time training, ArduinoÂ
Semantic Madurese Batik Search with Cultural Computing of Symbolic Impression Extraction and Analytical Aggregation of Color,Shape and Area Features
Get PDFLack of information media about Madurese batik Causes low awareness of younger generation to maintain the production of Madurese batik. Actually, Madurese Batik also has a high philosophy, which the motif and colour reflect the character of the Madurese. Madurese Batik has useful motif as a mean of traditional communication in the form of certain cultural symbols. We collected images of Madurese Batik by identifying the impression of Madurese Batik motif taken from several literature books of Madurese Batik and also the results of observation of experts or craftsmen who understand about Madurese Batik. This research proposed a new approach to create on application which can identify Madurese Batik impression by using 3D-CVQ feature extraction methods to extract color features, and used Hu Moment Invariant for feature feature extraction. Application searching of Madurese Batik image has two ways of searching, those are based on the image input Madurese Batik and based on the input of impression Madurese batik. We use 202 madurese batik motifs and use search techniques based on colors, shapes and aggregations (color and shape combinations). Â Performance results using based on image queries used: (1) based on color, the average precision 90%, (2) based on shape, the average precision 85%, (3) based on aggregation, the average precision 80%, the conclusion is the color as the best feature in image query. While the performance results using based on the impression query are: Â (1) based on color, the average value of true 6.7, total score 40.3, (2) based on shape, the average value of true 4.1, total score 24.1, and (3) based on the aggregation, the average value of true 2.5, the total score is 13.8, the conclusion is the color as the best feature in impression query
Data Mining Approach for Breast Cancer Patient Recovery
Get PDFBreast cancer is the second highest cancer type which attacked Indonesian women. There are several factors known related to encourage an increased risk of breast cancer, but especially in Indonesia that factors often depends on the treatment routinely. This research examines the determinant factors of breast cancer and measures the breast cancer patient data to build the useful classification model using data mining approach.The dataset was originally taken from one of Oncology Hospital in East Java, Indonesia, which consists of 1097 samples, 21 attributes and 2 classes. We used three different feature selection algorithms which are Information Gain, Fisher’s Discriminant Ratio and Chi-square to select the best attributes that have great contribution to the data. We applied Hierarchical K-means Clustering to remove attributes which have lowest contribution. Our experiment showed that only 14 of 21 original attributes have the highest contribution factor of the breast cancer data. The clustering algorithmdecreased the error ratio from 44.48% (using 21 original attributes) to 18.32% (using 14 most important attributes).We also applied the classification algorithm to build the classification model and measure the precision of breast cancer patient data. The comparison of classification algorithms between Naïve Bayes and Decision Tree were both given precision reach 92.76% and 92.99% respectively by leave-one-out cross validation. The information based on our data research, the breast cancer patient in Indonesia especially in East Java must be improved by the treatment routinely in the hospital to get early recover of breast cancer which it is related with adherence of patient