Agricultural and biological Engineering

A national centre for geospatial data has been established in Malaysia under the custodianship of the Malaysian Centre for GeoSpatial Data Infrastructure (MaCGDI). Within this backbone of national infrastructure, several secondary infrastructures are being planned to serve a multitude of users. This paper addresses one such application which is targeted at the farming community. Although web based technology has revolutionized the way information is traded or shared across the internet while ecommerce and information dissemination activities have brought great benefits, there are communities that have been left out due to their inability to purchase commercial web mapping software. One such community involves the semi-literate farmers in Malaysia. Thus, there is a need to provide and affordable solution while narrowing the knowledge gap between developers and users. A potential solution is through the use of open source technology which is generally accessible to all people in the world, anytime, anywhere without the need to purchase and install additional software. This study explores the use of open source software, Map Guide Open Source, PHP, Apache Web server and MySQL database. The study area selected was in the state of Selangor in Malaysia. The web-based system developed in this research allows the farmers to access the information about rice cultivation in their area. The system allows variable rate fertilizer application maps to be printed for the farmers. Farmers are aided by the historical data about yield per paddy lot and fertilizer application in the previous planting seasons. This information helps farmers to analyze and reflect on the best strategy for the coming growing season. The benefits of this work is that it allows information sharing among farmers especially on rice production, such as recommendations of fertilizer, and to provide equal access to web-based information from end-users to policy makers for improving the productivity and efficiency of rice production through precision farming. (Keywords: Web-based GIS, precision farming, open source)

In this paper, a new method of 2D inhomogeneous and non-parametric image registration with sub-pixel accuracy is proposed. The method is based on the invocation of deformation operators which imitate the deformations expected to be observed when a landslide occurs. The similarity between two images is measured by a similarity function which takes into consideration grey level value correlation and geometric deformation. The geometric deformation term ensures that the minimum necessary deformation compatible with the two images is employed. An extra term, ensuring maximum overlap between the two images is also incorporated, in order to avoid the pitfall of finding maximum correlation coefficient with minimum overlap. Sub-pixel accuracy is achieved by manipulating lists of pixels (real valued positions and corresponding grey values) rather than integer grid positions conventionally used to represent images. Landsat 5 TM images of southern Italy are used for the experiments.

Rice (Oryza Sativa L.) is the main food source in Malaysia. Thus, to fulfill the needs, continuous rice production is required. Appropriate amount of nitrogen (N) fertilizer is needed to ensure high production of rice. In this research, the effect of N to plant height, SPAD reading, biomass and yield were firstly studied. It was later followed by the estimation of biomass and yield using Terrestrial Laser Scanning (TLS) data. Different amount of N i.e. 0 kg/ha, 85 kg/ha, 170 kg/ha and 250 kg/ha were applied to MR 219 and MR 220 paddy. The 2-way ANOVA results showed that all parameters were significantly different at each N level. The highest reading was achieved at 250 kg/ha of N level; 70.46 cm (plant height), 39.13 (SPAD reading), 927.29 g/m2 (biomass) and 830.99 g/m2 (grain yield) respectively. Therefore, these parameters can be used to indicate the level of input nitrogen at the plant. Later, the plant height calculated using developed Crop Surface Model (CSM) of the Terrestrial...

Harvested paddy normally contains impurities including husk. This study focuses on the use of thermal imaging to detect husk. Heating and cooling treatment was applied to 20%, 40%, 60%, 100% husk and 100% seed to differentiate between husk and seeds due to heat transfer. From result, mean pixel of seed thermal image is higher compared to husks. It value at 25 s gave a suitable indicator to separate between seed and husk. The technique can be used to detect husk with 100% success rate for 20% and 40%, 98.33% for 60% and 97.67% for 100% husk, while 94.33% for 100% seeds.

Image from satellite is an example of remote sensing data. However, when the resolution of the available satellite image is too coarse and does not meet the required resolution, a process known as image re-sampling need to be employed, so a higher resolution version of the image could be obtained. Image re-sampling may involve interpolation, which is a process of allocating intensity value into a new generated pixel. Yet, interpolation method usually degrades the image quality. In this paper, five basic interpolation methods have been successfully implemented. These interpolation methods are nearest neighbor interpolation, bilinear interpolation, interpolation with smoothing filter, interpolation with sharpening filter, and interpolation with unsharp masking. The aim of this project is to find interpolation method that is suitable for remote sensing data. The method of our interest is the method that is easy to be implemented, but can preserve the quality of the data in term of sharpness and validness of the information. Based on the results, it is shown that all five interpolation methods tested in this research can produce good quality output when the resolution of input image is high. For low resolution input, only bilinear, smoothing filter and unsharp masking can preserve the quality of the image. However, this is only limited for interpolation with magnification factor less than 5. Bilinear, smoothing filter and unsharp masking are suitable to interpolate remote sensing data if the resolution of the input image is high enough.

In this paper, a new method of change detection and identification of forest area is proposed. It is based on local mutual information and image thresholding. In order to identify the forest change area, the image of local mutual information were thresholded using three different threshold value, i.e-0.5, 0 and 0.5. The result is a binary change image. Our result shows that the best threshold value of local mutual information is 0. It has been shown that by using this method, the problem on selecting the threshold value can be solved. This method is simple and suitable to be used to detect the changes area even for the images taken from different modality. For this research, IKONOS image with the resolution of 1.0 m dated 11 March 2002 and SPOT image with the resolution of 2.5 m dated 23 January 2008 in Shah Alam, Selangor have been used.

Basal Stem Rot (BSR) is a well-known disease that affecting the production of oil palm. Early disease detection is vital to manage the disease effectively. This study examined the potential use of Terrestrial Laser Scanning (TLS) data to analyse the properties of oil palm tree at canopy and trunk section for non-infected and infected BSR at different severity level of infection. In summary, area and perimeter at trunk section 150cm; and size of canopy shows significant relationship with the severity level of BSR with the Pearson correlation value of-0.571,-0.530 and-0.806, respectively.

A yield prediction model was developed using measured energy inputs data from 40 wetland paddy farms in Malaysia. Energy inputs from six sources were optimized using benchmarking and data envelopment analysis. The model developed based on Cobb-Douglas production function has coefficient of determination (R 2) of 91%. Analysis on the model revealed direct relationship of yield with machinery, fuel, fertilizer and pesticides energy expenditures and an inverse relationship of yield with seeding rate. Hence, suggesting the need to reduce farmers' present seeding rate of 149 kg/ha to the optimum seeding rate of 128 kg/ha for higher yield and cost reduction.

Nitrogen is an important variable for paddy farming management. The objectives of this study were to develop and test a new method to determine the status of nitrogen and chlorophyll content in rice leaf by analysing and considering all visible bands derived from images captured using a conventional digital camera. The images from the 6-pannel leaf colour chart were acquired using Basler Scout scA640-70fc under light-emitting diode lighting, in which principal component analysis was used to retain the lower order principal component to develop a new index. Digital photographs of the upper most collared leaf of rice (Oriza sativa L.), grown over a range of soils with different nitrogen treatments, were processed into 11 indices and IPCA through six growth stages. Also a conventional digital camera mounted to an unmanned aerial vehicle was used to acquire images over the rice canopy for the purpose of verification. The result indicated that the conventional digital camera at the both leaf (r = −0.81) and the canopy (r = 0.78) scale could be used as a sensor to determine the status of chlorophyll content in rice plants through different growth stages. This indicates that conventional low-cost digital cameras can be used for determining chlorophyll content and consequently for monitoring nitrogen content of the growing rice plant, thus offering a potentially inexpensive, fast, accurate and suitable tool for rice growers. Additionally, results confirmed that a low cost LARS system would be well suited for high spatial and temporal resolution images and data analysis for proper assessment of key nutrients in rice farming in a fast, inexpensive and non-destructive way.

Digital images of FFB from anthesis to harvesting stage were acquired and grouped into 25 maturity stages. K-means clustering technique was used to separate the images into three colours clusters that represent three FFB features, Fruitlet, Brown spine and Green spine. The relationship of Hue colour component and FFB maturity stages was established. The FFB was found to grow in three major stages, from week 0 to 5, week 6 to 14 and week 15 to 24. From the relationship a Growth Model was developed and was validated with actual maturity stage. The coefficient of determination, R 2 was 0.95.

The Chokanan mango (Mangifera indica) has a high commercial potential. Its sugar content increases as the colour changes during the maturation process. In this research, the relationship between the sweetness of the Chokanan mango and its mean pixel values in RGB and HSB colour space is analyzed. This information could be utilized in determining the level of sweetness of the Chokanan mango without destroying the fruit. A Keyence machine vision system was employed to capture the images of the mango in RGB and HSB colour spaces. Based on the findings, it could be concluded that hue not only has the highest correlation value (-0.916), but also has the lowest value of the standard deviation at all levels of sweetness compared to other colour components. It is possible to determine sweetness at Level 1 and Level 2 with a 100% success rate and a 87% success rate at Level 3.

Oil palm is a commercial crop that is important for its food value and as a biofuel, along with its other benefits towards the economy and human health. Currently, Malaysia cultivates approximately 5.64 million ha of oil palm. To date, a study identifying abandoned oil palm areas using satellite images is almost non-existent. Conventionally, the monitoring of abandoned oil palm lands is tedious and time consuming, especially over large areas. Hence, in this article, the capability of high resolution satellite image via Satellite Pour I'Observation de la Terre-6 (SPOT-6) products to extract abandoned oil palm areas was explored, as was the use of multi-temporal Landsat Operational Land Imager (OLI) imagery to develop the phenology of abandoned oil palm sites. Homogeneity measures derived through SPOT images played a more important role to identify abandoned oil palm than crop phenology characteristics extracted from high spectral resolution of Landsat images. With the advancement of object-oriented classification, monitoring of abandoned oil palm areas can be done semi-automatically with an accuracy of 92±1%.

The potential of laser light backscattering imaging was investigated for monitoring color parameters of seeded and seedless watermelons during storage. Two watermelon cultivars were harvested and stored for 3 weeks with seven measuring storage days (0, 4, 8, 12, 15, 18, and 21). The color parameters of watermelons were monitored using the conventional colorimetric methods (L*, a*, b*, C*, H*, and ∆E*) and laser light backscattering imaging system. A laser diode emitting at 658 nm and 30 mW power was used as a light source to obtain the backscattering image. The backscattering images were evaluated by the extraction of backscattering parameters based on the mean pixel values. The results showed that a good color prediction was achieved by the seedless watermelon with the R2 are all above 0.900. Thus, the application of the laser light backscattering imaging can be used for evaluating the color parameters of watermelons during the storage period.

The effect of chitosan/carrageenan and glycerol as edible coating materials in preserving the fresh longan fruits stored at ambient temperature was evaluated. The concentration of coating components played an important role in the process of controlling quality changes and quantity losses. Changes in fruits' weight loss, respiration rate and color were used as a measure of the coating's effectiveness. Results have shown that increase in the chitosan or carrageenan concentration led to significant (p < 0.05) decreases in water loss, weight loss and respiratory rate in coated fruits. However, in carrageenan-coated fruits, high increase in concentration (> 1.19%) of the carrageenan resulted in slight increases in water and weight losses. From the multiple response optimization analysis, a combination of 1.29% (w/v) chitosan with 0.42% glycerol and 1.49% (w/v) carrageenan with 0.03% glycerol were predicted to give the desired coating because they were able to preserve the longan by showing minimal quality changes and quantity losses. Efecto de los recubrimientos comestibles a base de chitosano y carragenano en los frutos de longan (Dimocarpus longan) después de la cosecha RESUMEN El presente estudio se propuso evaluar el efecto de materiales de recubrimiento comestibles a base de chitosán/carragenano en la conservación de frutos de longan frescos, almacenados a temperatura ambiente. La concentración de los componentes de recubrimiento desempeñó un rol importante en el proceso de control de los cambios de calidad y las pérdidas de cantidad. Los cambios en el peso, la tasa de respiración y el color fueron utilizados como medida de la eficacia del recubrimiento. Los resultados mostraron que al aumentar la concentración de quitosano o carragenano se redujo significativamente (p < 0.05) la pérdida de agua, la pérdida de peso y la tasa respiratoria en los frutos con recubrimiento. Sin embargo, en los frutos cubiertos con carragenano, el elevado aumento en su concentración (> 1.19%) produjo un ligero aumento del agua y pérdida de peso. El análisis de optimización de respuesta múltiple permitió pronosticar que la combinación de 1.29% (w/v) quitosano con 0.42% de glicerol y 1.49% (w/v) de carragenano con 0.03% glicerol producirían el recubrimiento deseado, pues pudieron conservar el longan con mínimos cambios en la calidad y mínimas pérdidas de cantidad.

Flood disasters are considered annual disasters in Malaysia due to their consistent occurrence. They are among the most dangerous disasters in the country. Lack of data during flood events is the main constraint to improving flood monitoring systems. With the rapid development of information technology, flood monitoring systems using a computer vision approach have gained attention over the last decade. Computer vision requires an image segmentation technique to understand the content of the image and to facilitate analysis. Various segmentation algorithms have been developed to improve results. This paper presents a comparative study of image segmentation techniques used in extracting water information from digital images. The segmentation methods were evaluated visually and statistically. To evaluate the segmentation methods statistically, the dice similarity coefficient and the Jaccard index were calculated to measure the similarity between the segmentation results and the ground...

Oil palm crops are essential for ensuring sustainable edible oil production, in which production is highly dependent on fertilizer applications. Using Landsat-8 imageries, the feasibility of macronutrient level classification with Machine Learning (ML) was studied. Variable rates of compost and inorganic fertilizer were applied to experimental plots and the following nutrients were studied: nitrogen (N), phosphorus (P), potassium (K), magnesium (Mg) and calcium (Ca). By applying image filters, separability metrics, vegetation indices (VI) and feature selection, spectral features for each plot were acquired and used with ML models to classify macronutrient levels of palm stands from chemical foliar analysis of their 17th frond. The models were calibrated and validated with 30 repetitions, with the best mean overall accuracy reported for N and K at 79.7 ± 4.3% and 76.6 ± 4.1% respectively, while accuracies for P, Mg and Ca could not be accurately classified due to the limitations of t...

Basal stem rot disease (BSR) in oil palm plants is caused by the Ganoderma boninense (G. boninense) fungus. BSR is a major disease that affects oil palm plantations in Malaysia and Indonesia. As of now, the only available sustaining measure is to prolong the life of oil palm trees since there has been no effective treatment for the BSR disease. This project used an ALOS PALSAR-2 image with dual polarization, Horizontal transmit and Horizontal receive (HH) and Horizontal transmit and Vertical receive (HV). The aims of this study were to (1) identify the potential backscatter variables; and (2) examine the performance of machine learning (ML) classifiers (Multilayer Perceptron (MLP) and Random Forest (RF) to classify oil palm trees that are non-infected and infected by G. boninense. The sample size consisted of 55 uninfected trees and 37 infected trees. We used the imbalance data approach (Synthetic Minority Over-Sampling Technique (SMOTE) in these classifications due to the differing...

Basal Stem Rot (BSR) is the most destructive disease instigated by a white wood rotting fungus called Ganoderma boninense, which cause great economic setback in oil palm productivity. It attacks the basal stem of oil palm trees, causing them to slowly rot. It also affects the xylem tissues that eventually interrupt water transportation to the upper part of the oil palm, turning the leaves at the frond become yellow. This problem should be prevented during nursery stage by separating between healthy and BSR-infected seedling. Therefore, this study focuses on the potential use of thermal imaging for detecting BSR in oil palm at seedling. Thermal images of oil palm seedling from healthy and BSR-infected were captured and processed to extract several thermal properties of the seedling, i.e., maximum, minimum, mean, and standard deviation of pixel intensity value. These values were then undergone statistical analysis to identify its significant different in differentiating healthy and BS...

Ganoderma boninense (G.boninense) is the causal agent of basal stem rot (BSR) which significantly reduced the productivity of oil palm plantations in Southeast Asia. At early stage, the disease did not show any physical symptoms that could be seen with naked eyes resulted in detection difficulties. To date, there was no effective detection for this disease, and conventional methods such as manual and laboratory-based required trained specialists as well as time-consuming. Therefore, this study was conducted using hyperspectral remote sensing to investigate the differences in spectral reflectance of young leaf (frond one (F1) of healthy and G. boninense infected oil palm seedlings. The seedlings were inoculated with G. boninense pathogen at five months old. At five months after inoculation, 558 spectral signatures of F1 were extracted from acquired hyperspectral images. Noise removal was done to the extracted spectral signatures to remove outliers in the data. Then, the spectral sign...