We propose a mobile gadget-based system for managing greenhouse plant production based on the Ubiquitous Environment Control System—Common Corresponding Message (UECS-CCM) standard. The system allows greenhouse growers to manage production from a mobile electronic device such as a smartphone or tablet instead of a PC. To select the best device operating system (OS) to use, we developed and tested sample software to display environmental data collected and transmitted by the UECS from a climate monitor in a greenhouse, under Google Android OS and Apple iOS. Although the software performed similarly under each OS, differences in the reproducibility of display contents and in procedures for installation led us to adopt Android OS.

View full abstract

The succession of agricultural techniques and skills is a critical issue in agricultural business management. However, to the best of our knowledge, no study has investigated systems that support the continuous measurement and visualization of agricultural operation data with the clear intention of addressing this issue. We developed a farming visualization system “FVS-PC Viewer” that continuously monitors various agricultural operation data, including operation content (target materials, machinery, etc.), locations, and status (video images), and integrates and visualizes these data so that operations can be recreated in a simulation. We conducted a field trial using this system, targeting actual machinery operations (rice paddy preparation). The field trial confirmed that our system is able to continuously measure agricultural operation data, such as a worker’s field-of-vision and site images (via two cameras), the operations route (via Geographical Positioning System), and machinery operations (via radiofrequency identification). The data could be synchronized automatically using the recording time as the primary key. Four workers who participated in the field test then trialing the simulated agricultural operation. They reported that entry-level and intermediate-level workers would be able to learn from the system, which includes commentary by experienced workers.

View full abstract

In this study, we extracted greenhouse sidewall control rules using a data mining method, based on data of time and the degree of sidewall opening, which is the main environmental management practice in greenhouses used to raise rice seedlings; the data were gathered by using an IC tag system (radio frequency identification). Decision trees were generated using the degree of sidewall opening as the target variable and weather information and growing days of seedlings as explanatory variables; rules satisfying the confidence and support constraints were extracted. Reasonable rules with high confidence and support resulted when the degree of sidewall opening was divided into three degrees. Cross-validation showed 75% correctness. Furthermore, individual rules extracted from decision trees generated using data from different parts of the day (morning, daytime, evening) had higher confidence and support than those based on whole-day data, and cross-validation showed >80% correctness. Multiple regression analysis resulted in a reasonable regression expression with a coefficient of determination of 0.7 and root mean square error of 19%. Precision of the regression was improved by analyzing data separately for of each part of day. Because many of the extracted rules were consistent with the subjective rules of farm laborers who work in the greenhouses, both decision tree analysis and multiple regression analysis had the capability of extracting the logic of workers to some extent.

View full abstract

Because Japanese farmers are aging, the need for cooperative working type agricultural robots that can perform tasks together with human beings is becoming particularly acute. Such robots need the ability to integrate their activities seamlessly with human beings and should possess functions that can be controlled intuitively, even by new agricultural workers and elderly people. These functions are generally considered under the heading of Kansei communication. Robots that incorporate such abilities include the Kansei Agri-robot and the Chinou robot, which can extract tacit knowledge and retain it for future use, and which have been the subject of intense study and development work. In this paper, we report on the fabrication and evaluation of an intuitive control component that utilizes human motions, which is one of the core technologies for issuing instructions, that is based on the Kinect sensor. The Kinect sensor, which can trace and replicate motion information based on a human skeleton movements, is a gaming device for the Xbox 360 released by Microsoft Corporation in 2010. It consists of three-dimensional depth sensors comprising an infrared (IR) emitter and an IR depth sensor, an RGB camera, and a multi-array microphone. The motion control technique targeted in this study is the finger pointing that will be used to instruct the robot on how to move and position itself correctly in a working area or other location. As the development environment, we used Microsoft Windows 7 as the operating system, OpenNI as the library, and NITE as the middleware. Visual Studio 2010 and the C++ language were used for software development. The following results were obtained. First, we found that the skeleton motion information of a farmer could be extracted at various angles using the Kinect sensor. Next, an algorithm for calculating finger-pointing points from the joint coordinate information relating to the shoulders, hands, and feet of the farmer was formulated. Based on the results of our verification experiments, we found that the algorithm accuracy was high when considered in terms of the assumed robot size and working area, and that control of a robot by finger pointing was possible. Estimation errors were found to vary depending on the sensing angle of the robot in relation to the farmer, and sensing errors from behind the farmer were greater than those occurring from other angles. It was also found that the Kinect sensor could be used in field conditions during early morning and late afternoon hours when light intensities had decreased, as well as under artificial lighting conditions.

View full abstract

Although information technology (IT) is common in intensive farming, it is uncommon in extensive farming. In this study, focusing on the effectiveness of information sharing, we applied IT to sugarcane, a major crop in the southwestern islands of Japan, as an example of extensive farming. We developed a mobile application termed “SugarNavi” to support harvest efficiency. Using SugarNavi on a smartphone or tablet, operators of harvesters upload their working locations and operation status to a server, which then changes the schedule of harvest plan according to location, status, and weather conditions. Typically, the information shared by farmers, harvest operators, and sugar refinery staff varies with the progress of harvest. This variation can limit the shared information. Instead, the functions of SugarNavi, information visualization and sharing, could be used to achieve consensus on the harvest schedule. Testing of SugarNavi by users allowed us to identify problems that we will face in actual use.

View full abstract

We developed an environmental measurement node that complies with application communication protocol version 1.00-E10 of the Ubiquitous Environmental Controlling System (UECS). The node consists of an Arduino Ethernet board with a newly developed electronic interface for the sensors in the measurement environment. A temperature and humidity sensor, a CO₂ sensor, and a solar cell (as photosynthesis photon flux sensor) were connected to it for testing. Software that we developed to operate it made it easy to change settings and adapt sensors. The node was installed in a plant factory with sunlight and connected to a UECS via a LAN. The apparatus operated as a UECS node, formatting the measurement values in accordance with the UECS protocol. Measured values of air temperature, humidity, and CO₂ concentration had estimated maximum errors of 1.17°C, 4.14%, and 49µmol mol^-1, respectively. These values (though not those of the light sensor) were accurate enough for practical use. The hardware design, software details, and UECS protocol are presented in full.

View full abstract