Ramli Adnan

Background modelling and background subtraction performance for object detection

Moving object detection in video applications is usually performed based on techniques such as background subtraction, optical flow and temporal differencing. The most popular literature technique approach to detect moving object from video sequences is background subtraction. This approach utilized mathematical model of static background and comparing it with every new frame of video sequence. In this paper, background subtraction technique using Mixture of Gaussian (MoG) method is conducted for detection of moving object at outdoor environment. Focus is specified at the five parameters of MoG namely background component weight threshold (TS), standard deviation scaling factor (D), user-define learning rate (α), Total number of Gaussian components (K) and Maximum number of components M in the background model (M) to give significant impact in producing the optimize background subtraction process. Experimental results showed that by varying each of the parameter can produce acceptable results that enable us to propose suitable parameter range of each parameter for detection of moving object in an outdoor environment.

Self-tuning fuzzy PID controller for electro-hydraulic cylinder

Hydraulic systems are widely used in industrial applications. This is due to its high speed of response with fast start, stop and speed reversal possible. The torque to inertia ratio is also large with resulting high acceleration capability. The nonlinear properties of hydraulic cylinder make the position tracking control design challenging. This paper presents the development and implementation of self-tuning fuzzy PID controller in controlling the position variation of electro-hydraulic actuator. The hydraulic system mathematical model is approximated using system identification technique. The simulation studies were done using Matlab Simulink environment. The output performance was compared with the design using pole-placement controller. The roots mean squared error for both techniques showed that self-tuning Fuzzy PID produced better result compared to using pole-placement controller.

Model identification and controller design for real-time control of hydraulic cylinder

Hydraulic cylinder has been widely used as an actuator in industrial equipments and processes due to its linear movements, fast response and accurate positioning of heavy load. The nonlinear properties of hydraulic cylinder has challenged researchers to design a suitable controller for position control, motion control, and tracking control. This paper presents model identification and controller design using pole-placement method for real-time control of hydraulic cylinder. The plant mathematical model was approximated using Matlab system identification toolbox from open-loop input-output experimental data. The simulation studies and real-time studies were done using Visual C++ console programming. The simulation and real-time results were compared and they show about similar performances.

Flood water level modeling and prediction using NARX neural network: Case study at Kelang river

Flood disaster has becomes major threat around the world because it causes loss of lives and damages to property. Thus, reliable flood prediction is very much needed in order to reduce the effects of flood disaster. Hence, an accurate flood water level prediction is an important task to achieve. Since flood water level fluctuation is highly nonlinear, it is very difficult to predict the flood water level. Artificial Neural Network is well known technique is solving nonlinear cases and Nonlinear Auto Regressive with Exogenous Input (NARX) model is one class of Artificial Neural Network model. Thus, this paper proposes flood water level modeling and prediction using Nonlinear Auto Regressive with Exogenous Input (NARX) model to overcome the nonlinearity problem and come out with an advanced neural network model for the prediction of flood water level 10 hours in advance. The input and output parameters used in this model are based on real-time data obtained from Department of Irrigation and Drainage Malaysia. Results showed that NARX model successfully predicted the flood water level 10 hours ahead of time.

Optimized PID control using Nelder-Mead method for electro-hydraulic actuator systems

Despite the application of advanced control technique to improve the performance of electro-hydraulic position control, PID control scheme seems able to produce satisfactory result. PID is preferable in industrial applications because it is simple and robust. The main problem in its application is to tune the parameters to its optimum values. This study will look into an optimization of PID parameters using Nelder-Mead approach for electro-hydraulic position control system. The electro-hydraulic system was represented by an ARX model structure obtained through MATLAB System Identification Toolbox. Second-order and third-order model of the system had been evaluated. Simulation and real-time studies show that ARX211 produced the best response in terms of transient speed and RMSE performance criteria even though the model has the least percentage of best fit.

Flood water level modelling and prediction using artificial neural network: Case study of Sungai Batu Pahat in Johor

Flood water level prediction has long been the earliest forecasting problems that have attracted the interest of many researchers. Accurate prediction of flood water level is extremely importance as an early warning system to the public to inform them about the possible incoming flood disaster. Using the collected data at the upstream and downstream station of a river, this paper proposes a modelling of flood water level at downstream station using back propagation neural network (BPN). In order to improve the prediction values, an extended Kalman filter was introduced at the output of the BPN. The introduction of extended Kalman filter at the output of BPN shows significant improvement to the prediction and tracking performance of the actual flood water level.

Real-time control of non-minimum phase electro-hydraulic system using trajectory-adaptive ZPETC

Hydraulic actuator has been widely used in industrial equipments and processes principally due to its high-power density and system solution that it can provided. The natural nonlinear property of hydraulic cylinder has challenged researchers in designing suitable controller for positioning control, motion control and tracking control. This paper proposes a controller design using trajectory-adaptive ZPETC without factorization of zeros and implementing real-time control to non-minimum phase electro-hydraulic system. Simulation and real-time experimental results were compared and evaluated and they show interesting tracking performances.

Trajectory zero phase error tracking control using comparing coefficients method

This paper presents the studies on trajectory zero phase error tracking control without factorisation of zeros polynomial where the controller parameters are determined using comparing coefficients methods. The controller was applied to two types of third-order non-minimum phase plant. The first plant was having a zero outside and far from the unity circle. Another plant was having a zero outside and near to the unity circle. Simulation and experimental results will be presented to discuss its tracking performance.

Artificial neural network modelling and flood water level prediction using extended Kalman filter

Accurate flood water level prediction are essential for reliable flood forecasting modelling. Although back propagation neural network (BPN) offer advantages for flood water level prediction, nonlinearity due to input parameters are the major issue to this modelling. A novel Extended Kalman Filter (EKF) optimization algorithm was employed in this study to overcome the nonlinearity problem and come out with an optimal ANN for the prediction of flood water level 3 hours in advance. The inputs used in the algorithm were current values of rainfall at the flood location and three upstream locations of river water levels. The BPN model was trained and tested successfully with Root Mean Square Error (RMSE) and loss function (V) close to zero.

New Artificial Neural Network and Extended Kalman Filter hybrid model of flood prediction system

Accurate prediction of flood water level is a difficult task to achieve due to the nonlinearity of the water level itself and lacking of input parameters to the neural network model. Although Artificial Neural Network is proven to be the best model of flood water level prediction, suitable model parameters need to be chosen for training purposes in order to arrive to an optimal model with smallest error. A new Back Propagation Neural Network model (BPN) for the prediction of flood water level 3 hours ahead of time is developed in this study. This optimized BPN model offers advantages of parameter analysis method instead of trial and error method for choosing the optimized BPN model parameters. However, the simulated results of BPN model required improvement as the model could not able to track the actual water level precisely. Hence, this paper proposes BPN model with integration of EKF at the output. Performance indices result such as Akaikes Final Prediction Error(FPE), Loss Function(V) and Root Mean Square Error (RMSE) from this hybrid model outperform the BPN model result.