Anuar Mohamed Kassim

Correction method of wind speed prediction system using predicted wind speed fluctuation

This paper describes a prediction of a wind speed fluctuation by using hierarchical neural network to improve the wind speed prediction. The future wind speed fluctuation (increase or decrease) is predicted with discrete value (1 or -1). The timing of the wind speed changes after 10 minutes is predicted. Time delay is confirmed during the predicted and observed values. Therefore, the timing of wind speed change is focused. Besides, the correction system of the wind speed prediction by using the fluctuation prediction result is proposed where two types of correction methods are applied. The wind speed prediction by applying RMSE method in the existence/absence of correction is evaluated. Finally, the application limit of correction when using fluctuation prediction result and effectiveness of predicting the wind speed fluctuation also will be considered.

Performance analysis of wireless warning device for upper body level of deaf-blind person

For blind people, it is generally very hard if not impossible to notice the obstacles which exist around them except by touching the objects and by hearing the information from around them. Especially the obstruction which is existed at upper level of body. The issue becomes more severe when a blind person also has multiple sensory problems such as impaired hearing. Conventionally, they rely on white canes or guide dogs to assist them in order to reach their desired destination safely. However, the conventional method is beneficial only if the obstructions are existed at below level of body. They could not sense and hear the surrounding and cannot recognize their locations. It is very hard for them to travel independently from one destination to another without the proper navigation tools. In this paper, the performance analyses of a wireless vibration warning device in order to sense the obstructions at upper level of body for deaf-blind people is described. Four pieces of vibrator are used in order to give warning signals when obstacles are detected by ultrasonic sensors which are mounted to detect the obstacle at four directions such as front, down, left and right. From the experiment which is conducted, the configuration of the vibrators in order to warn the user when the obstacles are detected is confirmed. The location and the response of the user are acquired from the experiment which has been done. By using the developed wireless vibration warning device, the upper body level obstacles can be detected without touching the object and the effective wireless vibration warning device functions successfully.

Motion control of nonlinear gantry crane system via priority-based fitness scheme in firefly algorithm

Advanced manufacturing technology made Gantry Crane System (GCS) is one of the suitable heavy machinery transporters and frequently employed in handling with huge materials. The interconnection of trolley movement and payload oscillation has a technical impact which needs to be considered. Once the trolley moves to the desired position with high speed, this will induce undesirable’s payload oscillation. This frequent unavoidable load swing causes an efficiency drop, load damages and even accidents. In this paper, a new control strategy of Firefly Algorithm (FA) will be developed to obtain five optimal controller parameters (PID and PD) via Priority-based Fitness Scheme (PFS). Combinations of these five parameters are utilized for controlling trolley movement and minimizing the angle of payload oscillation. This PFS is prioritized based on steady-state error (SSE), overshoot (OS) and settling time (Ts) according to the needs and circumstances. Lagrange equation will be chosen for modeling and simulation wi...