Search

This dataset comprises oil palm fresh fruit bunch (FFB) images that may potentially be used in the study related to fruit ripeness detection via image processing. The FFB dataset was collected from palm oil plantations in Johor, Negeri Sembilan, and Perak, Malaysia. The data collection involved acquiring pictures of FFB from various angles and classifying them based on their ripeness level, categorised into five classes: damaged bunch, empty bunch, unripe, ripe, and overripe. An experienced grader carefully labelled each FFB image with the corresponding ground truth information. The dataset provides valuable insights into the colour variations of FFBs throughout their ripening process, which is essential for assessing oil quality. It includes observations on the external fruit colours as well as characteristics related to the presence of empty sockets in the FFB as a key indicator of ripeness. The reusability potential of this dataset is significant for researchers in the field of oil palm fruit classification and grading, which requires an extensive outdoor dataset that comprise FFB's both on the tree and on the ground. Our work enables the development and validation of machine learning pipelines for outdoor automated FFB grading. Furthermore, the dataset may also support studies to improve oil palm cultivation practices, enhance yield, and optimise oil quality.

Undesirable vibrations resulting from the use of vibrating hand-held tools decrease the tool performance and user productivity. In addition, prolonged exposure to the vibration can cause ergonomic injuries known as the hand-arm vibration syndrome (HVAS). Therefore, it is very important to design a vibration suppression mechanism that can isolate or suppress the vibration transmission to the users’ hands to protect them from HAVS. While viscoelastic materials in anti-vibration gloves are used as the passive control approach, an active vibration control has shown to be more effective but requires the use of sensors, actuators and controllers. In this paper, the design of a controller for an anti-vibration glove is presented. The aim is to keep the level of vibrations transferred from the tool to the hands within a healthy zone. The paper also describes the formulation of the hand-glove system’s mathematical model and the design of a fuzzy parallel distributed compensation (PDC) controller that can cater for different hand masses. The performances of the proposed controller are evaluated through simulations and the results are benchmarked with two other active vibration control techniques-proportional integral derivative (PID) controller and active force controller (AFC). The simulation results show a superior performance of the proposed controller over the benchmark controllers. The designed PDC controller is able to suppress the vibration transferred to the user’s hand 93% and 85% better than the PID controller and the AFC, respectively.

In a modern small gasoline engine fuel injection system, the load of the engine is estimated based on the measurement of the manifold absolute pressure (MAP) sensor, which took place in the intake manifold. This paper present a more economical approach on estimating the MAP by using only the measurements of the throttle position and engine speed, resulting in lower implementation cost. The estimation was done via two-stage multilayer feed-forward neural network by combining Levenberg-Marquardt (LM) algorithm, Bayesian Regularization (BR) algorithm and Particle Swarm Optimization (PSO) algorithm. Based on the results found in 20 runs, the second variant of the hybrid algorithm yields a better network performance than the first variant of hybrid algorithm, LM, LM with BR and PSO by estimating the MAP closely to the simulated MAP values. By using a valid experimental training data, the estimator network that trained with the second variant of the hybrid algorithm showed the best performance among other algorithms when used in an actual retrofit fuel injection system (RFIS). The performance of the estimator was also validated in steady-state and transient condition by showing a closer MAP estimation to the actual value.