Dimas Firmanda Al Riza

Hourly Solar Radiation Estimation Using Ambient Temperature and Relative Humidity Data

This paper presents hourly solar radiation estimation methods using ambient temperature and relative humidity data. The methods are based on the decomposition model that is calculating each of solar radiation components, which depend on atmospheric transmittance. Two methods to predict atmospheric transmittance value using available meteorological data were proposed. In the first method, a decision matrix was used, while in the second method, regression correlation of meteorological parameters was used. The calculations results were evaluated using statistical parameter. Though the result shows both of the methods perform well, more satisfactory results were obtained from first method with Root Mean Square Error of 87.6 Watt/m 2 , Normalized Root Mean Square Error of 8.29%, correlation coefficient of 0.95 and index of agreement of 0.97. Furthermore, the first method only needs ambient temperature and relative humidity data that commonly measured in meteorological stations.

Potato feature prediction based on machine vision and 3D model rebuilding

Depth camera application, image processing for potato depth images.Potato 3D surface model rebuilding.Potato length, width, thickness, volume and mass prediction with mathematical models. Machine vision based on color, multispectral, and hyperspectral cameras to develop potato quality grading can be used to predict length, width, and mass, as well as defects on the interior and exterior of a sample. However, the images obtained by these cameras are limited by two-dimensional shape information, including width, length, and boundary. Other vital elements of appearance data related to potato mass and quality, including thickness, volume, and surface gradient changes are difficult to detect due to slight surface color differences and device limitations. In this study, we recorded the depth images of 110 potatoes using a depth camera, including samples with uniform shapes or with deformations (e.g., bumps and divots). A novel method was developed for estimating potato mass and shape information and three-dimensional models were built utilizing a new image processing algorithm for depth images. Other features, including length, width, thickness, and volume were also calculated as mass prediction related factors. Experimental results indicate that the proposed models accurately predict potato length, width, and thickness; the mean absolute errors for these predictions were 2.3mm, 2.1mm, and 2.4mm, respectively, while the mean percentage errors were 2.5%, 3.5%, and 4.4%. Mass prediction based on a 3D volume model for both normal and deformed potato samples proved to be more accurate compared to models based on area calculation. Thus 93% of samples were graded by the correct size group using the volume density model while only 73% were graded correctly using the area density. This depth image processing is an effective potential method for future non-destructive post-harvesting grading, especially for products where size, shape, and surface condition are important factors.

Applications of Intelligent Machine Vision in Plant Factory

Abstract Intelligent machine vision has been widely used in plant factory for many purposes. There are two aims in this study i.e. the first is improving the performance of intelligent machine vision for precision irrigation system using optimized feature selection technique and the second is developing intelligent machine vision for precision artificial lighting system using Light Emitting Diode (LED). The proposed feature selection technique used in the first aim is Neural-Discrete Hungry Roach Infestation Optimization (N-DHRIO) algorithm. The intelligent machine vision for precision irrigation system and the precision LED lighting system have successfully been developed, and it shows effective to control moisture content and light intensity of the plant precisely. In large scale plant factory, those systems can optimize plant growth and reduce the water consumption and energy costs.

Potential of using uric acid fluorescence in eye fluid for freshness assessment on Red Sea bream (Pagrus major)

Abstract Fluorescence characteristics of uric acid in Red Sea bream (Pagrus major) eye fluid was explored as a potential rapid and simple assessment for fish freshness. To investigate this, eye fluid samples were collected during storage at 22 ± 2 °C for standard uric acid measurements by high-performance liquid chromatography at 12 h intervals up until 36 h storage. Simultaneously, uric acid fluorescence spectroscopy measurements by fluorophotometer at 3 h intervals up until 36 h storage were made. High-performance liquid chromatography results showed the concentration of uric acid increased with storage time in the Red Sea bream eye fluid; changes similar to those observed in Japanese dace eye fluid, only differing in concentration and rate of accumulation. The fluorescence signals of uric acid in Red Sea bream eye fluid increased with storage time, which the high-performance liquid chromatography results confirmed. To further explore this, uric acid fluorescence signals were plotted against a standard fish freshness indicator “K value”, which is calculated from the concentration of adenosine triphosphate and its breakdown products using paper electrophoresis method. A good exponential relationship between these two parameters (determination coefficient of 0.94). A high linear correlation between the predicted K value from the uric acid fluorescence signals and the measured K value (determination coefficient of 0.94 and root mean square error of prediction of 6.37%) indicate uric acid fluorescence characteristics in fish eye fluid has a high potential to be employed as a new, fast and simple method to assess fish freshness.

Potato quality grading based on machine vision and 3D shape analysis

Abstract Machine vision is a non-destructive grading technology and cost-effective method with high accuracy that can be used to predict length, width, and mass, as well as defects of both interior and exterior of a sample by employing different cameras, such as color, multispectral, or hyperspectral cameras. To obtain certain data, which relates to sample quality in the 3D space (thickness, volume, and surface gradient distribution) and mass prediction, a novel method was developed and the obtained appearance quality was graded utilizing a new image processing algorithm for depth images. In this study, we recorded the depth images of 110 potatoes using a depth camera, including samples with uniform shapes or with deformations (e.g., bumps, bent shape, and divots). Length, width, thickness, and volume were calculated respectively, and used as key factors for detecting potato deformity, such as bent shape, bumps, and hollow. Experimental results indicate that mass prediction based on a volume model for both normal and deformed potato samples showed high accuracy, thus 90% of the samples were graded for the correct size group using the volume model. In addition, the appearance quality grading reached 88% of a correct percentage for bent shape, bump, and hollow defect detection by combining the surface data in 2D and 3D space. In addition, a potato virtual reality model rebuilding algorithm was developed for sample quality tracing and rechecking based on 3D shape and color images. This model redisplays the potato color and 3D shape data in multi-views and supports 360-degree rotation in both horizontal and vertical directions to simulate the in-hand examination experience. This depth image processing is an effective potential method for future non-destructive post-harvesting grading, especially for products where size, shape, and surface condition are important factors.