Oyas Wahyunggoro

UAV obstacle avoidance using potential field under dynamic environment

In this paper, the potential field principle is applied to several UAVs (Unmanned Aerial Vehicles) for optimal path planning. Each UAV has its own goals and it is used the attractive potential field to reach the goals. On the contrary, each UAV is considered as obstacle for other UAVs that must be avoided. In this research, there are two types of obstacles, i.e the static and dynamic. The repulsive potential field principle is used to avoid for both static and dynamic obstacles. The whole method is implemented into Parrot AR Drone 2.0 Quadcopter model of UAV and simulated in Gazebo Simulator by Robot Operating System (ROS). The results of this research are to control the thrust of quadcopter so that it is in flying position, the value of value of roll (α) or pitch (β) must set to not equal or approaching 90° or -90° and not between -180° and 180° or between -90° and 90°. Based on the dynamic obstacle performance test with parameter tuning, the optimal avoidance is when the η value is 7.8 while when in static and dynamic test with parameter tuning, the optimal avoidance is when the η value is 7.9 noted by the fastest time and the shortest path.

Control of a magnetic levitation system using feedback linearization

Dynamics of a magnetic levitation system are usually unstable and complicated. Therefore, a good controller is needed to achieve high-precision positioning of a ferromagnetic ball. This paper presents control of a magnetic levitation using exact feedback linearization controller. The dynamics of the system is analyzed by Euler-Lagrange. The mathematical model of the system shows that nonlinear. The original nonlinear system is transformed into an equivalent linear system using feedback linearization technique. The controller is simulated using matlab. The simulation results show that the controlled output can follow desire reference.

Effect of window length on performance of the elbow-joint angle prediction based on electromyography

The high performance of the elbow joint angle prediction is essential on the development of the devices based on electromyography (EMG) control. The performance of the prediction depends on the feature of extraction parameters such as window length. In this paper, we evaluated the effect of the window length on the performance of the elbow-joint angle prediction. The prediction algorithm consists of zero-crossing feature extraction and second order of Butterworth low pass filter. The feature was used to extract the EMG signal by varying window length. The EMG signal was collected from the biceps muscle while the elbow was moved in the flexion and extension motion. The subject performed the elbow motion by holding a 1-kg load and moved the elbow in different periods (12 seconds, 8 seconds and 6 seconds). The results indicated that the window length affected the performance of the prediction. The 250 window lengths yielded the best performance of the prediction algorithm of (mean±SD) root mean square error = 5.68%±1.53% and Persons correlation = 0.99±0.0059.

Modified sliding mode control with uncertainties behavior of a magnetic levitation system

This paper presents a magnetic levitation system driven by conventional sliding mode control and modified sliding mode control. The techniques will be investigated to know the robustness from uncertainties. High uncertainties make the controller not accurate because mismatches between mathematical model of the controller and dynamics of the magnetic levitation system. Variation uncertainties in the parameters of the magnetic levitation system were simulated using Matlab Simulink. The simulation results show that modified sliding mode control robust from uncertainties.

Analysis of emotional condition based on electrocardiogram signals

Emotion is a mental condition that appears spontaneously based on self-conscious effort and usually followed by physiological changes. Emotion is especially caused by stimulation. The related information with emotional condition by someone is communicated to all body through ECG. Therefore, it is important to conduct a research in analysis of emotion based on the measurement of ECG. Data emotion was categorised according to the stimulation that had been given to the subject by using video and music as long as ECG recorded. ICA method analysis with FastICA algorithm could be developed to obtain emotion feature. Feature classification was based on statistical approach from the independent component with higher of kurtosis value. The proposed method in classification was based on decision tree using Random Forest algorithm. The classification result shows that the emotional recognition based on ECG signals can be well implemented by system. The developed method successfully classifies the emotional condition from ECG signals. The method achieves the accuracy of 92.2% for identification of neutral emotion, 93.9% for negative emotion and 92.1% for positive emotion. The value of ICSI is obtained about 81.2% for neutral conditions, 88.3% for negative emotions and 85.1% for positive emotions, it means that the system is successfully to classify individually and effective for overall.

A hybrid feature selection method using multiclass SVM for diagnosis of erythemato-squamous disease

The diagnosis of erythemato-squamous disease is a complex problem and difficult to detect in dermatology. Besides that, it is a major cause of skin cancer. Data mining implementation in the medical field helps expert to diagnose precisely, accurately, and inexpensively. In this research, we use data mining technique to developed a diagnosis model based on multiclass SVM with a novel hybrid feature selection method to diagnose erythemato-squamous disease. Our hybrid feature selection method, named ChiGA (Chi Square and Genetic Algorithm), uses the advantages from filter and wrapper methods to select the optimal feature subset from original feature. Chi square used as filter method to remove redundant features and GA as wrapper method to select the ideal feature subset with SVM used as classifier. Experiment performed with 10 fold cross validation on erythemato-squamous diseases dataset taken from University of California Irvine (UCI) machine learning database. The experimental result shows that the proposed model based multiclass SVM with Chi Square and GA can give an optimum feature subset. There are 18 optimum features with 99.18% accuracy.The diagnosis of erythemato-squamous disease is a complex problem and difficult to detect in dermatology. Besides that, it is a major cause of skin cancer. Data mining implementation in the medical field helps expert to diagnose precisely, accurately, and inexpensively. In this research, we use data mining technique to developed a diagnosis model based on multiclass SVM with a novel hybrid feature selection method to diagnose erythemato-squamous disease. Our hybrid feature selection method, named ChiGA (Chi Square and Genetic Algorithm), uses the advantages from filter and wrapper methods to select the optimal feature subset from original feature. Chi square used as filter method to remove redundant features and GA as wrapper method to select the ideal feature subset with SVM used as classifier. Experiment performed with 10 fold cross validation on erythemato-squamous diseases dataset taken from University of California Irvine (UCI) machine learning database. The experimental result shows that the propose...

Trajectory and altitude controls for autonomous hover of a quadrotor based on fuzzy algorithm

A quadrotor is needed by geologists to do surveillance and monitoring in several disaster-prone areas. Therefore, quadrotors which are able to perform autonomous hovering in order to move from one location to another are required. Based on the problem, This paper presents the trajectory and altitude control for autonomous hovering of quadrotor by using fuzzy logic controller. This algorithm is applied to the altitude control that serves to control the quadrotor to hover at a specific position. It is also applied on the trajectory control so that the quadrotor will be able to move to x and y trajectories. The proposed algorithm shows that quadrotor can quickly hover at a predetermined height taking rise time in 1.5 second and settling time at 1.9 second. Furthermore, the quadrotor is able to move from the initial position to the next position with the rise time in 1.4 second and settling time at 2 second.

A comparative study on fuzzy Mamdani-Sugeno-Tsukamoto for the childhood tuberculosis diagnosis

World Health Organization (WHO) estimated that approximately 80 thousand children died every year in view of Childhood Tuberculosis. The disease needs an appropriate treatment considering the difficulties in establishing a diagnosis in pediatric patients. The incapability of children to produce sputum becomes one of the difficulties. Sputum is used to diagnose a person suffering from tuberculosis, based on Mycobacterium tuberculosis in sputum. In this paper, Mamdani, Tsukamoto and Sugeno-types Fuzzy Inference System are applied to assist the tuberculosis diagnosis. The different technique in these three methods is aimed to determine the most appropriate method for such diagnosis. The results show that, of the three types of Fuzzy Inference System, the best model is Sugeno model. Sugeno-type FIS has a better accuracy compared to both Mamdani and Tsukamoto ones at 93%, equivalent to a fault diagnosis in 13 of 180 patients. Here, Mamdani-type FIS is provided the diagnostic accuracy of 89%, equivalent to the ...

3D OBJECT MODELING USING DATA FUSION FROM LASER SENSOR ON QUADROTOR

Environmental modeling of a robot which is needed for robot navigation and path planning is in the form of planar or 2D modeling. Several previous researchers have used laser sensor to model 2D obstacles because it has data accuracy for navigation. It is in a planar shape and implemented in quadrotor thus the obstacle modeling formed is in 2D. The problem in a 2D environment is that the path planning and navigation of the robot requires a considerable time because the robot stops at loca minima and attempts to find other paths in the dimension. The problem can be solved by using combined data taken from the laser sensor. The combination of the data uses several algorithms such as graph theory and vector field histogram algorithms. Therefore, this paper presents the combination of the algorithms to model a 3D environment. By using this model, the quadrotor is able to avoid loca minima.

A novel Q-scanning for convex hull algorithm

Convex hull is one of the important part of computational geometry. Many applications have used this method as part of their system. In this research, the novel Q-scanning of convex hull algorithm is proposed. The algorithm reduces computational complexity of conventional convex hull algorithm. The initial step of the proposed method is dividing the problem of convex hull into four subset hull. Each hull has its extreme point. In the process, the extreme point will move until meet convergence. The proof of the concept is conducted in Matlab software. The method of the experimental setup is a convex construction hull from some finite points of natural number which set randomly. The experiment shows that the algorithm is able to build a convex hull with O(n) of computational complexity and can be used as alternative approach for convex hull problem.