Fish disease is considered the main cause for production and economic losses by fish farmers. Fish disease detection and health monitoring is a demanding task by manual method of human visualization. Therefore, any potential approach that is fast, reliable and possesses high automation supports an interest in this issue. Nowadays, with the current emergence in the technology revolution, image processing has been extensively used in disease detection field, especially in human and plant, aiding the human experts in providing the right treatment. Image processing technique offers opportunities to improve the traditional approach in achieving accurate results. Besides, several steps in image processing are adopted including image acquisition, image pre-processing, image segmentation, object detection, feature extraction and classification. The objective of this paper is to briefly review the work established in the fish disease detection field with the use of numerous classification techniques of image processing, including rule-based expert system, machine learning, deep learning, statistical method and hybrid method. The present review recognizes the need for improvement in these image processing approaches that would be valuable for further advancement in terms of performance.
1 November 2019 in Journal of Physics: Conference Series
Jaundice is describes as yellow discoloration of the skin and other tissues of a newborn infant. It happens when the bilirubin pigment rises up to 5 mg/dL or 85 μmol/L due the organs just started to developed. 75% of newborns in Malaysia had jaundice in the first week of life. Conventional assessment method is not convenient since it unable to detect all type of human skin colours, caused traumatization and costly. This research work proposed jaundice detection system based on the colour card technique that represent all types of human skin colours. This research does not involve any subject due to parent’s cooperation and ethics limitation. The input data is represented by the colour card shades. It represents random bilirubin colour in patient’s body, all types of human skin colour, and standard reference bilirubin concentration colour. It acquires input data by capturing different type of colour card shades using OPT101 photodiode sensor and USB4000-XR1-ES spectrometer. The input data collected were verified through Anderson-Darling normality test and analysed using Pearson’s correlation coefficient to measure the strength of the association between the two variables for each input sample tested. Based on the correlation results, it shows high correlation value (r=0.997). Percentage error analysis is used to validate the experimental device and shows value of 9.90% which prove this technique is reliable. The significant contributions of this work is the improvement of the accuracy in detecting jaundice level for all type of human skin colours through this system.
1 October 2021 in Journal of Physics: Conference Series
This paper focuses on the ongoing development of real-time monitoring system with implementing the Internet of Things (IoT) element for arsenic heavy metal concentration in paddy field using pH sensor for data collection. The pH sensor will detect the hydrogen ion concentration from the prepared soil put in pot contained with various arsenic concentration. The developed system is then compared with the pH sensor in the market to verify its accuracy and sensitivity. The collected data will be transferred wirelessly into data cloud so that it can store the previous and current reading data. Besides, the system’s function is also to ensure the safeness of paddy plant to be planted with knowing the right amount of arsenic concentration can be passed.