Rohani S. Mohamed Farook

Feasibility Study on Plant Chili Disease Detection Using Image Processing Techniques

Producing chili is a daunting task as the plant is exposed to the attacks from various micro-organisms and bacterial diseases and pests. The symptoms of the attacks are usually distinguished through the leaves, stems or fruit inspection. This paper discusses the effective way used in performing early detection of chili disease through leaf features inspection. Leaf image is captured and processed to determine the health status of each plant. Currently the chemicals are applied to the plants periodically without considering the requirement of each plant. This technique will ensure that the chemicals only applied when the plants are detected to be effected with the diseases. The image processing techniques are used to perform hundreds of chili disease images. The plant chili disease detection through leaf image and data processing techniques is very useful and inexpensive system especially for assisting farmers in monitoring the big plantation area.

Data Mining on Climatic Factors for Harumanis Mango Yield Prediction

Yield Prediction is an essential task to be achieved in order to implement effective forward marketing. Forward marketing is a contract that will be signed between supplier and client based on the amount of delivery and the price of delivery in future. To be able to sign such a contract the supplier should be very confident that the yield could be achieved. The yield sustainability is a challenging process in agriculture. Mango cultivar Harumanis is one of the best table tropical fruit due to its aroma and sweetness. Despite its overwhelming local demand in Malaysia and also internationally, the fruit supply never meets the demand. The flowering phase is identified as an important stage as plant reproductive physiology. Currently, Harumanis mango flowering only happens once a year that restricts the yield. In this paper, data mining is used to quantify the climatic effects on Harumanis mango yield to enable yield prediction.

Design of a capacitive sensor for oil palm fresh fruit bunch maturity grading

Automatic grading of oil palm fresh fruit bunch is desired. In this study, a capacitive sensing system was designed and developed for the purpose of grading oil palm fresh fruit bunch. In this method, oil palm fresh fruit bunch placed between capacitive plates as a dielectric material and then measure the resulting capacitance voltage. Experiments were carried out using oil palm bunches of Tenera variety. Ripe and unripe mature bunches tested with 100 kHz sinusoidal frequencies. Correlation of capacitive response observed to be linear to bunch weight and negative linear to bunch ripeness. This result suggest that this method be explored for automatic grading of oil palm fresh fruit bunch.

P2.9.27 Development of a Decision Support System for Brackish Aquafarm Management Using Electronic Tongue

This paper presents the findings in developing a decision support in assessing brackish water quality using an electronic taste sensing system made up of sensor array and signal processing tools. Seven ionic sensors and precision centigrade temperature sensor fused together as an array. Developed graphical user interface displays real time measurement and pattern based prediction. Results of periodic test on prepared brackish water solutions showed that the system differentiates samples of varying salinity (0.01 to 0.5 Mol of NaCl per liter), supporting the system usage as salinity detection instrument in aquafarms. Incorporation of temperature sensor increases system stability to temperature drift. System robustness showed that three ionic sensors sufficiently differentiate sixdecade dilution of brackish solution.