• Journal of Biosystems Engineering
• /
• v.38 no.3
• /
• pp.192-198
• /
• 2013

Purpose: Methods for non-destructive estimation of product quality have been reported in various industrial fields, but the application of ultrasonic techniques for the agricultural products of potatoes, pears, apples, watermelons, kiwis and tomatoes etc. have been rarely reported since the application of a contact-type ultrasonic transducer in agricultural products is very difficult. Therefore, this study sought to determine the firmness of apples using non-contact ultrasonic techniques. Methods: For this experiment, an ultrasonic experimental tester using a non-contact ultrasonic transducer was created, and a signal processing program was used to analyze the acquired ultrasonic reflected signal. Also, a universal testing machine was used to measure firmness parameters of the apples such as bioyield strength, a firmness factor, after the ultrasonic tests had been performed. Results: Six distance correction factors were calculated to obtain consistent values of ultrasonic properties regardless of the distance between the transducer and the surface of the subject. We developed prediction models of the bioyield strength using the distance correction factors. Conclusions: The optimum prediction model of the bioyield strength of apples using a non-contact ultrasonic technique was a multiple regression model ($R^2=0.9402$).

• International Journal of Computer Science & Network Security
• /
• v.22 no.12
• /
• pp.71-78
• /
• 2022

Electronic measuring devices have an important role in agricultural projects and in various fields. Electronic measuring devices play a vital role in controlling and saving soil information. They are designed to measure the temperature, acidity and moisture of the soil. In this paper, a new methodology to manage irrigation and soil fertility using an electronic system is proposed. This is designed to operate the electronic irrigation and adds inorganic fertilizers automatically. This paper also explains the concept of remote management and control of agricultural projects using electronic soil measurement devices. The proposed methodology is aimed at managing the electronic irrigation process, reading the moisture percentage, elements of soil and controlling the addition of inorganic fertilizers. The system also helps in sending alert messages to the user when an error occurs in measuring the percentage of soil moisture specified for crop and a warning message when change happens to the fertility of soil as many workers find difficulty in daily checking of soil and operating agricultural machines such as irrigation machine and soil fertilizing machine, especially in large projects.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1414-1430
• /
• 2022

Due to the Internet of Things popularity, many agricultural data are collected by sensors automatically. The abundance of agricultural data makes precise prediction of rice yield possible. Because the climate factors have an essential effect on the rice yield, we considered the climate factors in the prediction model. Accordingly, this paper proposes a machine learning model for rice yield prediction in Taiwan, including the genetic algorithm and support vector regression model. The dataset of this study includes the meteorological data from the Central Weather Bureau and rice yield of Taiwan from 2003 to 2019. The experimental results show the performance of the proposed model is nearly 30% better than MARS, RF, ANN, and SVR models. The most important climate factors affecting the rice yield are the total sunshine hours, the number of rainfall days, and the temperature.The proposed model also offers three advantages: (a) the proposed model can be used in different geographical regions with high prediction accuracies; (b) the proposed model has a high explanatory ability because it could select the important climate factors which affect rice yield; (c) the proposed model is more suitable for predicting rice yield because it provides higher reliability and stability for predicting. The proposed model can assist the government in making sustainable agricultural policies.

• Journal of Biosystems Engineering
• /
• v.24 no.1
• /
• pp.59-66
• /
• 1999

Weed identification is important for precision farming. A machine vision system was applied to detect weeds. Shape features were analyzed with the binary images obtained from color images of radish, purslane, goosefoot, and crabgrass. Features studied were aspect, roundness, compactness, elongation, PTB, LTP, LTW, and PTAL of each plant. Discriminant analysis was used to classify plant species. The best shape features that distinguished crabgrass were LTP and LTW which distinguished the crabgrass from the others with 100%. Two dimensional discrimination by using LTP and PTB appeared to be effective for distinguishing radish, purslane, and goosefoot.

• Journal of Biosystems Engineering
• /
• v.40 no.4
• /
• pp.320-326
• /
• 2015

Purpose: Kimbugak is one of Korea's traditional snack foods made of laver. Mechanization of the manufacturing process is necessary to produce kimbugak in large quantities and standardize the products for industrialization. This study was conducted to develop a machine that can simultaneously accomplish the two processes of pasting and garnishing for manufacturing kimbugak, and test its performance. Methods: A pasting and garnishing machine was designed, and its target work efficiency was set at 720 sheets/h. The performance was tested based on the physical characteristics such as work efficiency, pasting uniformity, and garnishing uniformity. Results: With the developed technology, kimbugak could be produced up to a productive rate of 840 sheets/h on a single machine. The pasting uniformity ranged from 91.5% to 96.8%, and a garnishing uniformity of more than 90% could be obtained. Conclusions: It is expected that this approach to developing a machine with the functions of pasting and garnishing can contribute to the mechanization of the manufacturing process to produce Korean traditional foods including kimbugak in large quantities and standardize the products for industrialization.

• Journal of Biosystems Engineering
• /
• v.32 no.3
• /
• pp.160-165
• /
• 2007

This study was conducted to evaluate beef using a color machine vision system. The machine vision system has an advantage to measure larger area than a colorimeter and also could measure other quality factors like distribution of fats. However, the machine vision measurement is affected by system components. To measure the beef color with the machine vision system, the effect of color balancing control was tested and calibration model was developed. Neural network for color calibration which learned reference color patches showed a high correlation with colorimeter in L*a*b* coordinates and had an adaptability at various measurement environments. The trained network showed a very high correlation with the colorimeter when measuring beef color.

• Journal of Biosystems Engineering
• /
• v.22 no.2
• /
• pp.210-216
• /
• 1997

A study to select ground colors of Fuji apple for maturity index which are needed to standardize grading of the apples is presented. Two extreme colors of immature and fully mature Fuji and Zonagold apples produced in Korea were determined. Various ground colors of Fuji apple between the two extreme colors were collected and classified by human vision and colors of Fuji apple for maturity index were selected from the classification. Coordinates of the selected colors in xy chromaticity diagram were determined by spectrophotometers to define them in a standard coordinate system. Coordinates of the colors in r-g chromaticity diagram using a color machine vision system were also determined to use the colors in apple grading by the machine vision system. Grading Fuji apples using the machine vision system was performed and result of the grading was compared with Ending results of human vision and colorimeter. The comparison was performed with the same Fuji apple samples and showed 65% md 75% of same grades, respectively, as the grades determined by the machine vision system. Differences of fading performance between the compared three grading methods were explained as mainly because of the differences of observation area of the grading methods.

• Journal of Biosystems Engineering
• /
• v.33 no.3
• /
• pp.186-195
• /
• 2008

In this paper, a prototype tele-operative system with a mobile base was developed in order to automate cultivation of house melon. A man-machine interactive hybrid decision-making system via tele-operative task interface was proposed to overcome limitations of computer image recognition. Identifying house melon including position data from the field image was critical to automate cultivation. And it was not simple especially when melon is covered partly by leaves and stems. The developed system was composed of 5 major modules: (a) main remote monitoring and task control module, (b) wireless remote image acquisition and data transmission module, (c) three-wheel mobile base mounted with a 4 dof articulated type robot manipulator (d) exchangeable modular type end tools, and (e) melon storage module. The system was operated through the graphic user interface using touch screen monitor and wireless data communication among operator, computer, and machine. Once task was selected from the task control and monitoring module, the analog signal of the color image of the field was captured and transmitted to the host computer using R.F. module by wireless. A sequence of algorithms to identify location and size of a melon was performed based on the local image processing. Laboratory experiment showed the developed prototype system showed the practical feasibility of automating various cultivating tasks of house melon.

• Korean Journal of Agricultural Science
• /
• v.47 no.3
• /
• pp.471-483
• /
• 2020

Flood prediction is an important issue to prevent damages by flood inundation caused by increasing high-intensity rainfall with climate change. In recent years, machine learning algorithms have been receiving attention in many scientific fields including hydrology, water resources, natural hazards, etc. The performance of a machine learning algorithm was investigated to predict the water elevation of a river in this study. The aim of this study was to develop a new method for securing a large enough lead time for flood defenses by predicting river water elevation using the a long- short-term memory (LSTM) technique. The water elevation data at the Oisong gauging station were selected to evaluate its applicability. The test data were the water elevation data measured by K-water from 15 February 2013 to 26 August 2018, approximately 5 years 6 months, at 1 hour intervals. To investigate the predictability of the data in terms of the data characteristics and the lead time of the prediction data, the data were divided into the same interval data (group-A) and time average data (group-B) set. Next, the predictability was evaluated by constructing a total of 36 cases. Based on the results, group-A had a more stable water elevation prediction skill compared to group-B with a lead time from 1 to 6 h. Thus, the LSTM technique using only measured water elevation data can be used for securing the appropriate lead time for flood defense in a river.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.2
• /
• pp.51-60
• /
• 2021

Effective nonpoint source (NPS) pollution management requires frequent water quality monitoring, which is, however, often costly to be implemented in practice. Statistical techniques and machine learning methods allow us to identify and focus on fundamental environmental variables that have close relationships with NPS pollutants of interest. This study developed surrogate models to predict the concentrations of suspended sediment (SS) and total phosphorus (T-P) from turbidity and runoff discharge rates using multiple linear regression (MLR) and random forest (RF) methods. The RF models provided acceptable performance in predicting SS and T-P, especially when runoff discharge rates were high. The RF models outperformed the MLR models in all the cases. Such finding highlights the potential of RF techniques and models as a tool to identify fundamental environmental variables that are measured in relatively inexpensive ways or freely available but still able to provide information required to quantify the concentrations of NP S pollutants. The analysis of relative importance rates showed that the temporal variations of SS and T-P concentrations could be more effectively explained by that of turbidity than runoff discharge rate. This study demonstrated that the advanced statistical techniques such as machine learning could help to improve the efficiency of NPS pollutants monitoring.