Language：English   Publishing type：Research paper (scientific journal)   Publisher：MDPI AG  

One of the essential factors in the root zone environment that affects plant growth is temperature. Determining the optimal root zone temperature condition in a hydroponic system during cultivation could lead to an improvement in plant growth. An optimal control strategy can be determined by identifying the eco‐physiological process using a dynamic model. However, it is difficult to develop a dynamic model of the responses of plant growth to root zone temperature because the eco‐physiological processes of plants are quite complicated. We propose an intelligent approach that can deal with this complex system. Non‐linear autoregressive with exogenous input (NARX) neural networks were used to develop a dynamic model of the responses of plant growth to root zone temperature. The responses of chili pepper plant growth as affected by root zone temperature were measured during 60 days of cultivation inside a growth chamber using a non-destructive and continuous system based on a load cell. Five datasets of dynamic responses of plant growth were obtained for system identification. The results suggest that the application of a neural network is useful for modeling the dynamic response of plant growth to root zone temperature in hydroponic cultivation, with promising performance.

DOI： 10.3390/agriculture10060234

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

This study was conducted to investigate the effect of passive evaporative cooler on storage behavior - that is visual appearance, physiological loss in weight (PLW), color development, firmness, total soluble solids (TSS) and pH level of hot water treated eggplant fruit (Solanum melongena L.). Fresh harvested fruits were treated with hot water at 45°C for 1 h. The highest percentage of PLW (2.39%) was the fruit stored at ambient temperature of 25°C for nine days whereas the lowest percentage of weight loss (2.27%) was the fruit stored inside the passive evaporative cooler. In all cases, the decreasing rate of lightness (L* value) and increasing rate of greenness (a* value) and yellowness (b* value) of the hot water treated fruits were almost negligible. Firmness value of the fruits stored inside the passive evaporative cooler was found almost constant, while it reduced in fruits which stored at ambient temperature. Furthermore, higher TSS and lower pH value were observed in those fruits which were stored inside the passive evaporative cooler. In conclusion, the shelf life and quality of eggplant fruits can be extended using passive evaporative cooler.

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Biotron Institute  

An estimation based on a mathematical model to predict hourly evapotranspiration (ET) rates that occur inside a plant factory system was made using the Stanghellini model. The Stanghellini model is considered more appropriate for estimating the rate of ET inside the soilless culture of greenhouse tomatoes. The model requires some climatic data (e.g., solar radiation, air temperature, relative humidity, and wind speed) and plant growth parameters (leaf area index) as inputs. In this study, the observed data were obtained from an experimental greenhouse located at the Ehime University, Japan. The ET rate of tomato (Lycopersicon esculentum Mill.) crop was measured using a weighing method. Accurate determination of ET is essential to precisely compute crop water use and to assist growers for applying good irrigation management. The results showed that solar radiation and vapor pressure deficit are important factors driving the ET rate. The model's output showed good results for determining the ET rate and depicted crop water requirements on an hourly basis.

DOI： 10.2525/ecb.52.183

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

A low cost 'Zero Energy Cool Chamber (ZECC)' has been developed for storing fruits and vegetables by using passive evaporative mechanism. This paper presents the results of a survey on the farmer's opinion regarding the exploitation of zero energy storage system. This survey was conducted at Mymensingh district of Bangladesh from 2011 to 2012 and it also revealed that most of the farmers sell their produce to the middlemen just after the harvest. Lack of transportation facility, shortage of energy supply and lack of investment on storage, lower price of vegetables during the harvesting season, farmers in the rural areas often sell their products to the middleman or in the local market at low prices. They are not even able to get the return of invested money of cultivating vegetables or fruits. As a result, higher percentage of poverty level remains in farmer's community. They demanded low cost storage system such as zero energy storage system which doesn't require electricity for operating to store their agricultural produces.

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：ELSEVIER SCI LTD  

A 'Zero Energy Cool Chamber (ZECC)' has been developed for storing fruits and vegetables from the viewpoints of low cost and energy savings. Adding water to a filler between the outer and inner brick walls and shade curtains is effective way to reduce the inside temperature of a ZECC. The objective of this study was to minimize the inside temperature by controlling the watering using an intelligent optimization technique (IOT) combined with neural networks (NN) and genetic algorithms (GA). The objective function was given by the average value of the inside temperature for one day. For dynamic optimization, the control process (24 h) was divided into 8 steps, and the optimal value (8-step ON-OFF intervals) of watering was obtained using NN and GA. In this method, dynamic changes in the inside temperature of the ZECC, as affected by the watering strategy, outside temperature and inside relative humidity conditions, were first identified using NN, and then the optimal value, which minimized the objective function, was determined through simulation of the identified NN model using GA. The average inside temperature for this optimal control was 4 degrees C lower than that for the continuous watering for 24 h, and was also 7.5 degrees C lower than that for no watering. The ZECC with the optimal watering strategy extended the shelf-life of tomato from 7 to 16 days. Thus, it was concluded that a ZECC optimized by using NN and GA is useful for storing tomato with no electric energy. (C) 2013 Elsevier B.V. All rights reserved.

DOI： 10.1016/j.compag.2013.04.008

Web of Science

researchmap

T. Morimoto, M. Islam and K. Hatou, &quot;An Intelligent Control Technique for Dynamic Optimization of Temperature during Fruit Storage Process,&quot; American Journal of Operations Research, Vol. 3 No. 1A, 2013, pp. 207-216.<br />
Agricultural control systems are characterized by complexity and uncertainly. A skilled grower can deal well with crops based on his own intuition and experience. In this study, an intelligent optimization technique mimicking the simple thinking process of a skilled grower is proposed and then applied to dynamic optimization of temperature that mini- mizes the water loss in fruit during storage. It is supposed that the simple thinking process of a skilled grower consists of two steps: 1) “learning and modeling” through experience and 2) “selection and decision of an optimal value” th- rough simulation of a mental model built in his brain by the learning. An intelligent control technique proposed here consists of a decision system and a feedback control system. In the decision system, the dynamic change in the rate of water loss as affected by temperature was first identified and modeled using neural networks (“learning and modeling”), and then the optimal value (l-step set points) of temperature that minimized the rate of water loss was searched for through simulation of the identified neural-network model using genetic algorithms (“selection and decision”). The control process for 8 days was divided into 8 steps. Two types of optimal values, a single heat stress application, such as 40°C, 15°C, 15°C, 15°C, 15°C, 15°C, 15°C and 15°C, and a double heat stress application, such as 40°C, 15°C, 40°C, 15°C, 15°C, 15°C, 15°C and 15°C, were obtained under the range of 15°C ≤ T ≤ 40°C. These results suggest that appli- cation of heat stress to fruit is effective in maintaining freshness of fruit during storage.

DOI： 10.4236/ajor.2013.31A020

researchmap

Other Link： http://orcid.org/0000-0001-5931-853X

M.P. Islam, T. Morimoto and K. Hatou (2013) Optimization of Watering for Minimizing the Inside Temperature of Zero Energy Cool Chamber for Storing Fruits and Vegetables. Proceedings of the 2013 IFAC bio-robotics Conference, Osaka Prefecture University, Japan, March, 27-29: 9-10.<br />
A zero energy cool chamber (ZECC) has been developed for storing fruits and vegetables from the viewpoints of low installation and operating cost. The inside temperature of the ZECC is cooled by adding water to a sand and zeolite based filler between the brick walls based on the principles of a natural evaporative cooling mechanism. The objective of this study was to minimize the inside temperature of the ZECC by controlling watering operation using an intelligent optimization technique combined with neural network and genetic algorithm. The objective function was given by the average value of the inside temperature for one day. For optimization, the control process (24 hours) was divided into 8 steps, and the optimal value (8-step ON-OFF intervals) of watering was obtained using neural networks and genetic algorithms. In this method, dynamic changes in the inside temperature of the ZECC, as affected by the watering strategy and outside temperature, were first identified using neural network, and then the optimal value, which minimized the objective function, was determined through simulation of the identified neural-network model using genetic algorithm. The average inside temperature for this optimal ON-OFF control was 5°C lower than that for the simple ON-OFF watering for 24 hours, and was also 8°C lower than that for no watering. The ZECC with the optimal ON-OFF watering strategy extended the shelf-life of untreated tomato from 7 to 16 days. Thus, it was concluded that a ZECC optimized by using neural networks and genetic algorithms is useful for storing tomato with no electric energy.

DOI： 10.3182/20130327-3-JP-3017.00007

researchmap

Other Link： http://orcid.org/0000-0001-5931-853X

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IFAC Secretariat  

A simulation based on mathematical model to predict the daily evapotranspiration rates that occur inside the controlled-environmental systems was simulated using the Simulink toolbox in MATLAB program. Four inputs data were used in this model (e.g. solar radiation, air temperature, relative humidity, and wind speed). The output of this simulation model is the estimation of the daily evapotranspiration (ET) rates that depict the crop water requirement.

DOI： 10.3182/20130327-3-jp-3017.00010

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IFAC Secretariat  

To resolve the problem of declination of Japanese agriculture, plant factories with automation, quality control, robotization and speaking plant approach are necessary. The multi operation system described in this paper has running unit with automatic position sensing. Growth environment measurement unit has transpiration, photosynthesis, distance and temperature sensors to obtain plant growth information. The pest control unit uses the antiseptic effect of ozone water. The harvesting unit is used for cucumbers that grow fast
recognition of cucumbers ready to be harvested is achieved through distance information gathered by an attached photo interrupter and distance sensors. The development of multi-operation robot is continued by developing controlling program that can change the operating pattern by sharing the contents by each controlling and operating unit.

DOI： 10.3182/20130327-3-jp-3017.00066

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IFAC Secretariat  

In intelligent greenhouse, balance of yield with heating cost is one of important point for manager. In this study, we constructed growing model of tomato based on accumulated temperature in greenhouse, predictive model of air temperature inside greenhouse based on weather forecast, and heating load model in greenhouse. Then using these models, we developed the application to support manager's decision by predicting yield of tomato, and flower differentiation date, flowering date, harvest start date and harvest end date of each stage, and furl cost of heating.

DOI： 10.3182/20130327-3-jp-3017.00017

Scopus

researchmap

Language：English   Publishing type：Research paper (conference, symposium, etc.)  

Tomato fruits were harvested at the accurate stage of maturity age and stored inside the zero energy cool chamber (ZECC) which has a shelf-life of only about 7 days at ambient temperature (25°C). Storing tomato inside the ZECC could be a practical technique at farmer&#039;s field to extend storage life by reducing the quality degradation. Physiological loss in weight (PLW) was faster for fruits held at ambient temperature. Weight loss during the storage at ambient temperature was 5.4%, but untreated fruits at ZECC over the same period showed a 2.6% loss. Although soluble solids increased over the storage period, there were no significant differences between ZECC and ambient temperature. However effect of hot water treatment (60°C for 3 minutes) on quality of tomatoes was clearly visible by increasing storage life up to 29 days. It reduced weight loss and decay, inhibited color development and maintained firmness of tomatoes but had no effect on total content of soluble solids and pH level. Hot water treatment slightly reduced the mold growth of tomatoes stored inside ZECC.

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：American Society of Agricultural and Biological Engineers  

Air temperature in greenhouse is high for tomato plants in summer. It is important to maintain optimum temperature in greenhouse for yield. The cost of whole cooling in greenhouse is so expensive that local temperature control is suggested. Our previous research showed tomato plants with root cooling at 25°C increased yields compared with those with no cooling. The chilled water can be used for root cooling system in greenhouse. The objective of this research was to evaluate the root cooling system using cold water for growing tomato plants in summer. Tomato plants were grown hydroponically in greenhouse. The cooling water flows into PVC pipe which is installed under cultivation bed. Water temperature was maintained at 12°C. Inlet and outlet water in pipe and rockwool temperatures were measured. Our results showed that the rockwool temperature was maintained around 22°C with high air temperature (30°C) using root cooling system.

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：International Society for Horticultural Science  

Chlorophyll fluorescence is red light emitted from chlorophyll a pigments in green leaf. Hence, accurate measurement of chlorophyll fluorescence allows us to assess photosynthetic functions, which can be used as indicator of a plant's health conditions. By illuminating a dark-adapted green leaf with an excitation light at a stable intensity, a dynamic change in chlorophyll fluorescence intensity can be observed. This phenomenon is called "chlorophyll fluorescence induction phenomenon" and the time course of the chlorophyll fluorescence intensity during this phenomenon is called "induction curve". The shape of the induction curve varies depending on the plant's health conditions. In this study, we developed a chlorophyll fluorescence imaging system to monitor health conditions of tomato plants in greenhouse by measuring the induction curves. First, we applied this system to detect physiological changes caused by high light treatment at the whole plant level to check its performance. Then, we extended this system to the plant canopy level. A 60×60 cm LED panel provided measuring light to illuminate the leaves around the shoot apex of the tomato plant. The induced chlorophyll fluorescence was measured by a CCD camera fixed in the middle of the LED panel. The intensity of the measuring light at the plant surface was about PPFD 100 μmol m -2 s-1. All of the chlorophyll fluorescence imaging was performed at night. We measured the induction curves of 20 tomato plants grown in a north-south cultivation lane. Most of the induction curves of the tomato plants showed common shapes. However, two plants showed unusual shapes of induction curves. Seven days after the induction curve measurement, a visible symptom of physiological dysfunction was observed in one of the two plants. This study showed that chlorophyll fluorescence imaging is a promising technique for monitoring of health conditions of tomato plants in a greenhouse.

DOI： 10.17660/ActaHortic.2011.893.29

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：INT SOC HORTICULTURAL SCIENCE  

The chlorophyll fluorescence imaging technique is useful to evaluate the photosynthetic functions of living plants. In our previous study, we developed a chlorophyll fluorescence imaging system for full-size tomato plants in a greenhouse. This system images the chlorophyll fluorescence induction phenomenon, a dynamic change in chlorophyll fluorescence intensity induced by an excitation light under dark condition and analyzes the shape of the induction curve, i.e., the time course of the chlorophyll fluorescence intensity during this phenomenon. The shape of the induction curve is characterized with the initial maximum peak (P), the following transient dip (S) and secondary small peak (M). We defined a photosynthetic function index (PFI; the fluorescence intensity of P divided by the average fluorescence intensity from S to M) to evaluate the shape of the induction curve. In this study, we applied this system to evaluate the photosynthetic functions of tomato plants grown under different night air temperatures during winter and to detect the difference in photosynthetic functions of two tomato cultivars, i.e., 'Reika' and 'Tomimaru', in a greenhouse. The PFI of the plants grown under relatively low night air temperature (11 degrees C) was significantly lower than that of the plants grown under normal night air temperature (15 degrees C). The PFI of 'Tomimaru' was significantly higher than that of 'Reika'. The differences in PFIs would be partly due to the differences in the chlorophyll pigments compositions.

DOI： 10.17660/ActaHortic.2011.907.55

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

The present study aimed to diagnose the hanging of the stress to the plant by using images. The position where the influence of the stress appears first was a flower. Shape changes into the flower that receives the stress. Therefore, it was assumed that the stress condition of the plant can be diagnosed from the morphological characteristics such as a shape of the flower. The substantial change appears in the number of sheets of the petal, the number of stigma, and the size of the flower. An image diagnosis system for detecting the strength of the stress occurred in the plant was developed using an artificial neural networks. © 2011 IFAC.

DOI： 10.3182/20110828-6-IT-1002.02875

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

The chlorophyll fluorescence imaging technique is useful for evaluating photosynthetic functions of plants without actually touching the plant. In our previous study, we developed a chlorophyll fluorescence imaging system for tomato plants cultivated in greenhouses. This imaging system measures the chlorophyll fluorescence induction phenomenon, a dynamic change in chlorophyll fluorescence intensity induced by illuminating a dark-adapted leaf with a stable intensity excitation light, and analyzes the shape of the induction curve, i.e., the temporal course of chlorophyll fluorescence intensity during this phenomenon. The shape of the induction curve is characterized by an initial maximum peak (P), subsequent transient dip (S), and secondary small peak (M). We defined an index, the photosynthetic function index (PFI
fluorescence intensity of P divided by the average fluorescence intensity from S to M), to evaluate the shape of the induction curve. In this study, we applied this system to detect drought stress in tomato plants cultivated in a semi-commercial greenhouse. PFI was clearly lower in stressed plants than in healthy plants. The decreased PFI in stressed plants is probably attributable to photosynthetic dysfunction in these plants. © 2011 IFAC.

DOI： 10.3182/20110828-6-IT-1002.01490

Scopus

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)   Publisher：The Society of Eco-Engineering  

Chlorophyll fluorescence imaging is a useful tool to assess photosynthetic ability of plant leaf without contact. By applying an actinic light of stable intensity to dark adapted leaf, a dynamic change in chlorophyll fluorescence intensity can be induced. This dynamic change in chlorophyll fluorescence intensity is called &ldquo;Induction phenomenon&rdquo;. &ldquo;Induction method&rdquo; is a representative way to detect photosynthetic dysfunction in plant leaf by analyzing the induction phenomenon. In this study, we investigated whether imaging of chlorophyll fluorescence induction phenomenon induced by weak actinic light at a PPFD of 10 &mu;mol m<SUP>-2</SUP>s<SUP>-1</SUP> can detect photoinhibition, which is caused by strong light irradiation treatments at PPFDs of 500, 1000 and 2000 &mu;mol m<SUP>-2</SUP>s<SUP>-1</SUP> for 1 hour. As a result, the photoinhibition in individual tomato leaves caused by the strong light irradiation treatments could be detected by measuring chlorophyll fluorescence induction phenomena that were induced by the weak actinic light. Furthermore, continuous measurement of chlorophyll fluorescence induction phenomena during a relaxation of photoinhibition under dark condition for 24 hours proved that P value, i.e. maximum chlorophyll fluorescence intensity in chlorophyll fluorescence induction phenomenon, can be used as an index of photoinhibition.

DOI： 10.11450/seitaikogaku.21.69

CiNii Books

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

Mature green tomatoes were treated by a single heat stress which is a hot water (HW) or a hot air (HA) and a double heat stress which is the combination of HA + HW or HW + HA before holding in the storage chamber at 15°C for 10 days. The rate of water loss was evaluated using prestorage hot water treatment at temperature 35-45°C from 5-60 minutes and hot air at 40°C for 1-24 h. The double heat stress technique used either hot water followed by hot air (HW + HA) or hot air followed by hot water (HA + HW). The findings suggest that 6 h of hot air was beneficial in reducing weight loss both in short term as well as long-term tomato storage. The use of hot air followed by hot water was also found effective in reducing water loss and preserving freshness of tomato during storage. Also, the prestorage use of hot air at 40°C for 24 h prevent the chilling injury and consequently prolong the storage of tomatoes after holding at -2.2°C for two weeks and then at 20°C for another 10 days.

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：JAPAN INT RESEARCH CENTER AGRICULTURAL SCIENCES  

This paper presents the results of a survey on the situation of farmers, their problems and feasibility of heat stress techniques during storage of fruits and vegetables in Pakistan. In addition, consumer perception was also surveyed regarding availability and quality of stored fruits and vegetables. The survey, which was conducted at Dera Ismail Khan District of Pakistan's North West Frontier Province during 2004, revealed that most of the farmers sell all their produce in the market just after harvest. This might be either due to the unavailability of storage facilities or the high cost to store low and medium value fruits/vegetables. High electricity costs and frequent power cuts further raised the storage prices. However, among different methods practiced locally, sun drying was the most popular method. Regarding consumer perception, the majority were not satisfied about availability of fruits and vegetables in the market all the year round. Lack of storage facilities, damages that occurred during transportation, improper packaging, the role of middlemen, and huge influx of produce in a short time were the major reasons given for reducing availability of fruits and vegetables to consumers on the one hand and lowering returns to growers on the other. The growers demanded subsidized governmental storage facilities to store their agricultural commodities.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Biotron Institute  

Tomato cultivation in large-scale plant factories is expanding in Japan. It is therefore important to measure the leaf area and growth of tomato accurately in the plant factory for estimating the yield. In this study, the area of tomato leaves was measured using a three-dimensional range meter. The models, which estimated the whole area of the tomato plant, were then developed using the area of a part of non-destructively measured leaf. The parameter necessary for the modeling was designed by taking the leaf position on tomato plant into account. As a result, a practical model for measuring the tomato leaf area non-destructively was developed.

DOI： 10.2525/ecb.44.173

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

In the plant factory, successful agricultural production can be carried out under controlled environmental conditions. However, the yield and quality improvement of tomato is the major problem in a plant factory. It is necessary to ensure the optimal utilization of photosynthetic efficiency throughout tomato growth stages in order to solve this problem. In the present study, all the environmental factors, including light, water etc necessary for the photosynthesis, were systematically controlled. The leaves are the main parts of the plant where photosynthesis occurs. To measure the leaf are non-destructively, a model was constructed which calculated the area of the whole branch from the tip leaf. The utilization pattern of the leaf and the effective leaf were also considered in the model construction. Similarly another model, which calculated the area of the whole branch using length of the leaf and the branch in case the tip leaf area could not be measured, was also developed. For the modeling, the decision procedure of utilization pattern of the leaf and length of the branch was also examined. The effective leaf at the tip, taken as standard, was 0.4 times bigger than ordinary leaf. It was found that the accuracy of the leaf area could be improved on the utilization pattern of the leaf, when it is divided into the group of leaves in the growth phases and the leaves at the end of growth. It was also noted that the accuracy of the leaf area was improved, when the length of the branch was defined from the base of the leaf, which is near to the stem to the base of the tip leaf. © 2005 SICE.

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IFAC Secretariat  

To improve the quality of Satsuma mandarin during the developing and maturing stages, an optimal watering operation was investigated through identification and optimization using intelligent control techniques. Dynamic changes in the sugar content and the citric acid of Satsuma mandarin, as affected by rainfall and sunshine duration, was first identified using neural networks, and then an optimal operation for watering (rainfall management) that maximizes the sugar content and that minimizes the citric acid of Satsuma mandarin was sought through simulation of the identified neural-network model using genetic algorithms. an optimal solution obtained here was an operation that increases the amount of watering during the first stage and then markedly reduces it during the latter half stage of the maturing stage. From simulation, the maximization of the amount of watering during the first stage resulted in a significant decrease in the citric acid, and the minimization during the latter half stage led to a marked increase in the sugar content. A mulching technique with plastic film and a sprinkling operation allow controlling the amount of rainfall. This operation suggests a better way for supplying the water to Satsuma mandarin and improving the quality. Copyright © 2005 IFAC.

DOI： 10.3182/20050703-6-cz-1902.02096

Scopus

researchmap

Language：Japanese   Publisher：JAPANESE SOCIETY OF AGRICULTURAL, BIOLOGICAL AND ENVIRONMENTAL ENGINEERS AND SCIENTISTS  

Acoustic responses obtained by striking the fruit have been used for evaluating fruit firmness and maturity using a FFT method. However, those responses are often quite complex and uncertain. This study proposes a new technique to address such complex data. In the method, the attractor of the acoustic response is first described; then, its slope is calculated using the method of least squares. There was a close relationship between the slope of attractor and fruit firmness. The slope of attractor decreased in proportion to fruit firmness. Significant linearity was observed in the relationship between fruit firmness and the slope of attractor. This linearity was confirmed through simulation of a mechanical model (damped vibration model). These results showed that use of the attractor allowed quantitative evaluation of fruit firmness in the time-domain.

DOI： 10.2525/jshita.15.224

CiNii Books

researchmap

Other Link： https://jlc.jst.go.jp/DN/JALC/00234496556?from=CiNii

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：PERGAMON-ELSEVIER SCIENCE LTD  

In this study, the algorithm, which separated the strawberry fruit at high speed using chain code for separating the fruit at high speed, was examined. Harvesting robot that it used in this study has installed the manipulator to rectangular coordinate robots of the three-axial style. CCD camera installed it at the tip of the manipulator, and the image of the strawberry is incorporated in the computer using this camera. There is the resolution of the image at length of 320 pixels, width of 200 pixels, and 16 bits per one pixel. The procedure of the image processing was done, as it was shown in the following. 1. The input of the image from CCD camera. 2. The recognition of the group of the fruit by the binarization processing. 3. Noise rejection and compensation of the contour data. 4. The separation of the fruit in the harvest time. 5. The separation of the fruit according to the chain code.
It was proven that CCD camera and distance to the fruit were the important factors which decide the recognition speed in this experiment. At CCD camera and distance of the fruit, it was proven that the time for the recognition slowed down, when leaving recognition rate lowers, and when it closes. It is considered the reason why the time for the recognition slowed down that the data increased for the image processing, and that therefore, the calculation amount increased. Then, it was possible to shorten the whole processing time by advancing the optimization of the program. By the optimization of the program, the processing time was almost able to be shortened by 3 seconds. Copyright (C) 2001 IFAC.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：PERGAMON-ELSEVIER SCIENCE LTD  

Image processing of the planting equipment is reported. The outline of the planting machine has been composed of belt conveyor and planting equipment which supply the nursery plants. CCD camera for image input was installed above the belt conveyor. The basic action in belt conveyor of the planting equipment is two described in the following. They are that it controls the speed of the belt conveyor by the interval of the seedling in order to efficiently do, and that it removes the nursery plants of the immaturity. Therefore, the data to be got by the image processing are the intervals of the nursery plants and positions of the nursery plants of the immaturity. This system has done practical application with the purpose, and maximum speed of the planting equipment is the 5 plants per second. Copyright (C) 2001 IFAC.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：PERGAMON PRESS LTD  

In this study, a 3-dimentional visual sensor system was developed to separate and recognize overlapped strawberry fruit. This system is composed of three units. (I) a CCD camera for detecting the fruits based on the color image, (2) a range finder unit for separating overlapped fruits and measuring the distance and (3) computers for analyzing 2D- and 3D-data. This system finds out the cutting point of peduncle on the fruit based on the recognizing data. Using a 3-dimentional visual sensor system, it is found that the shapes of the fruits selected can be successfully recognized. It detects the cutting point of peduncle for a robot harvesting.

Web of Science

researchmap

Language：Japanese   Publisher：Japanese Society of Agricultural, Biological and Environmental Engineers and Scientists  

A local area network (LAN) for a plant factory was designed. In this LAN, three types of computers, an AT computer (AI), a workstation (WS) and a terminal computer (TC) were connected by Ethernet.<BR>The file transfer speeds between the computers by using FTP command were examined as the following 4 conditions; (1) TC was used as a client and WS was used as a server, (2) WS was used as a client and AT was used as a server, (3) AT was used as a client and WS was used as a server and (4) TC was used as a client and AT was used as a server. The file transfer speed was the fastest in the condition (1), and the slowest in the condition (3) .<BR>Furthermore, other two data acquisition commands in addition to FTP command were used in order to characterize the condition (1) . The two commands were COPY command in Network File System (NFS) and ONE LINE COPY command in NFS. A file transfer speed from TC to WS was the highest when FTP command was sent. A file transfer speed from WS to TC was the highest when COPY command in NFS was sent.<BR>The effect of the file size on the file transfer speed in the condition (1) was tested by using the following three file sizes; 768, 000 bytes, 384, 000 bytes and 96, 000 bytes. File transfer speed was the same when COPY command and ONE LINE COPY command in NFS were used, i.e. independent on the size of files. However, when FTP command was used, larger size files were transferred faster than smaller size files. Thus, it was found that large file sizes such as image data could be transferred most effectively between computers by using FTP command.

DOI： 10.2525/ecb1963.30.81

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：PERGAMON PRESS LTD  

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Publ by Pergamon Press Inc  

Greenhouse production of vegetables has been remarkably developed. Furthermore, vegetables could be cultivated in the factory where such environmental factors as light intensity and temperature are controlled just like in process industries. In the system, many computers are used for environmental control, nutrient control and management of cultivation. Of course, the artificial intelligence is also introduced for the expert system for control and diagnosis of the cultivated vegetables. On the other hand, progress in automated mechanization for seeding and transplanting has made 'greenhouse automation' fit for practical use just like 'factory automation (FA)' in industries. Now, process industries are rationalized based on the concept of so called 'Computer Integrated Manufacture (CIM)'. Therefore, it might be noted that the system in the agricultural production such as the vegetable factory should also be considered based on the concept of CIM. That is the 'Computer Integrated Agricultural Production (CIAP)'. In this paper, we examine the vegetable factory from the 'CIAP' point of view. Computer network composed of both usual personal computer for environmental control and the special computer for the artificial intelligence is examined. It seems evident that the CIAP discussed in this paper is expected as the most effective system in the coming generation.

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：PERGAMON PRESS LTD  

Web of Science

researchmap

Publisher：Japanese Society of Agricultural, Biological and Environmental Engineers and Scientists  

As the first step of application of AI (Artificial Intelligence) to agriculture, an expert system was constructed. This system makes diagnoses of disease and insect damage of satsuma mandarin and also suggests control methods for better growth. The system was constructed on 'NEC PC-9801' personal computer, using 'Sogen' which is a Japanese expert shell. Knowledge on disease and insect damage was rearranged and expressed in production rules, composing knowledge base.<BR>The expert system works well and makes correct diagnoses. In the future, such applications of AI would be more important in agriculture.

DOI： 10.2525/ecb1963.26.185

researchmap

Language：Japanese   Publisher：養賢堂  

CiNii Books

researchmap

Language：Japanese   Publisher：The Japan Society of Mechanical Engineers  

For establishment and the spread of the intelligent greenhouse which stably enabled farming, the high quality and the stable supply are essential tasks. Moreover, the environmental control and delicate cultivation management are necessary for implementation. Then, we developed the autonomous travelling robot diagnosing plant growth for the tomato cultivation. This robot collects the plant diagnosis information such as the temperature of the leaf and the photosynthesis function with the self-position in the intelligent greenhouse. As a result, this study showed that the growth diagnosing robot was a promising technique for monitoring of the health condition of the tomato crops in the intelligent greenhouse.

CiNii Books

researchmap

Language：Japanese  

DOI： 10.2525/shita.21.59

J-GLOBAL

researchmap

Language：Japanese  

CiNii Books

researchmap

Language：English   Publisher：Biotron Institute  

Hot air and hot water are being extensively studied as postharvest heat treatments for retaining freshness and extending shelf life of many fruits and vegetables during storage. In the present study, the best combination of several types of heat stress application methods that minimizes water loss of fruit during storage were investigated, aiming at the practical use. The heat stress application allowed the water loss of the fruit during storage to be successfully reduced. The combinatorial double heat shock treatment where the hot air was first applied for 6 h at 40°C followed by hot water dipping for 6-12 h at 40°C showed the best performance at the final stage in all other treatments including single hot air, hot water, hot water + hot air and control (nonheated) in minimizing the water loss of oranges during storage. This heat stress technique (HA + HW) is useful for successful storage of orange.

DOI： 10.2525/ecb.44.31

Scopus

researchmap

Language：English   Publisher：Biotron Institute  

Hot air and hot water are being extensively studied as postharvest heat treatments for retaining freshness and extending shelf life of many fruits and vegetables during storage. In the present study, the best combination of several types of heat stress application methods that minimizes water loss of fruit during storage were investigated, aiming at the practical use. The heat stress application allowed the water loss of the fruit during storage to be successfully reduced. The combinatorial double heat shock treatment where the hot air was first applied for 6 h at 40°C followed by hot water dipping for 6-12 h at 40°C showed the best performance at the final stage in all other treatments including single hot air, hot water, hot water + hot air and control (nonheated) in minimizing the water loss of oranges during storage. This heat stress technique (HA + HW) is useful for successful storage of orange.

DOI： 10.2525/ecb.44.31

Scopus

researchmap

Language：Japanese  

CiNii Books

researchmap

Language：English   Publisher：AMER SOC AGRICULTURAL ENGINEERS  

In this study, dynamic optimization of heat treatment for reducing the water loss in fruit during storage was investigated using intelligent approaches. Over a temperature range from 15degreesC to 40degreesC, the control process was divided into 1 steps (1 = 6). The dynamic change in the rate of water loss as affected by temperature was first identified using neural networks, and then the optimal combination of the l-step setpoints for temperature that minimized the rate of water loss was searched for through simulation of the identified model using genetic algorithms. Two types of optimal values, a single application of heat stress and a double application of heat stress, were obtained under the range of 15degreesC &lt; T &lt; 40degreesC. The length of each step was 24 h. The former treatment is useful for short-term storage, and the latter is useful for comparatively long-term storage. With the single heat treatment, the temperature first rises to the highest level (40degreesC), which is maintained over a period of 24 h, and then suddenly drops to the lowest level (15degreesC). In particular, the sudden drop in temperature from the highest level to the lowest level provided lower values of the rate of water loss than maintaining the temperature constantly at the lowest level throughout the control process. These results suggest that application of heat stress to fruit is effective in maintaining freshness of fruit during storage.

DOI： 10.13031/2013.13938

Web of Science

researchmap

researchmap

researchmap

DOI： 10.2525/ecb1963.40.75

researchmap

Language：Japanese  

DOI： 10.2525/ecb1963.40.75

CiNii Books

researchmap

DOI： 10.2525/ecb1963.40.75

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

DOI： 10.2525/jshita.12.23

researchmap

DOI： 10.2525/jshita.12.23

researchmap

DOI： 10.2525/jshita.12.23

researchmap

DOI： 10.2525/jshita.12.23

researchmap

DOI： 10.2525/jshita.12.23

CiNii Books

researchmap

Language：Japanese   Publisher：JAPANESE SOCIETY OF AGRICULTURAL, BIOLOGICAL AND ENVIRONMENTAL ENGINEERS AND SCIENTISTS  

To reduce the prevalence of illness and detect physiological disorders in their early stages, pathological diagnosis of plants is important. When a plant image stored as a large data file is sent, transmission takes a long time. To reduce transmission time, image compression is needed. The most widely used compression format for photographs is JPEG (Joint Photographic Experts Group). The advantage of JPEG is its high compression rate. A weak point is irreversibility; it is impossible to reproduce the image perfectly.<BR>We use plant images for pathology diagnosis and investigated an algorithm to compress such images without loss of information. We adopted a method that separates the photographic image into useful parts (plant) and other parts (background), and stores and compresses only the useful part. The algorithm is as follows : I. Mask to get the plant information for diagnosis from a photographic image; 2. Delete the background; 3. Compress and store the image of only the plant image. We wrote a program to recognize and to mask the plants based on HSI (Hue, Saturation, Intensity). The program covers not only green vegetables, but also fruits. Furthermore, the program was investigated in combination with existing image compression techniques (for example, tiff and tga). We achieved a compression rate of about 45% compared with original photographs. We expect the compression rate to be increased in the future by optimizing the HSI parameters.

DOI： 10.2525/jshita.11.267

CiNii Books

researchmap

Other Link： https://jlc.jst.go.jp/DN/JALC/00057773599?from=CiNii

researchmap

researchmap

researchmap

researchmap

Language：Japanese   Publisher：JAPANESE SOCIETY OF AGRICULTURAL, BIOLOGICAL AND ENVIRONMENTAL ENGINEERS AND SCIENTISTS  

To reduce the prevalence of illness and detect physiological disorders in their early stages, pathological diagnosis of plants is important. When a plant image stored as a large data file is sent, transmission takes a long time. To reduce transmission time, image compression is needed. The most widely used compression format for photographs is JPEG (Joint Photographic Experts Group). The advantage of JPEG is its high compression rate. A weak point is irreversibility; it is impossible to reproduce the image perfectly.<BR>We use plant images for pathology diagnosis and investigated an algorithm to compress such images without loss of information. We adopted a method that separates the photographic image into useful parts (plant) and other parts (background), and stores and compresses only the useful part. The algorithm is as follows : I. Mask to get the plant information for diagnosis from a photographic image; 2. Delete the background; 3. Compress and store the image of only the plant image. We wrote a program to recognize and to mask the plants based on HSI (Hue, Saturation, Intensity). The program covers not only green vegetables, but also fruits. Furthermore, the program was investigated in combination with existing image compression techniques (for example, tiff and tga). We achieved a compression rate of about 45% compared with original photographs. We expect the compression rate to be increased in the future by optimizing the HSI parameters.

DOI： 10.2525/jshita.11.267

CiNii Books

researchmap

Other Link： https://jlc.jst.go.jp/DN/JALC/00057773599?from=CiNii

Language：Japanese   Publisher：JAPANESE SOCIETY OF AGRICULTURAL, BIOLOGICAL AND ENVIRONMENTAL ENGINEERS AND SCIENTISTS  

To reduce the prevalence of illness and detect physiological disorders in their early stages, pathological diagnosis of plants is important. When a plant image stored as a large data file is sent, transmission takes a long time. To reduce transmission time, image compression is needed. The most widely used compression format for photographs is JPEG (Joint Photographic Experts Group). The advantage of JPEG is its high compression rate. A weak point is irreversibility; it is impossible to reproduce the image perfectly.<BR>We use plant images for pathology diagnosis and investigated an algorithm to compress such images without loss of information. We adopted a method that separates the photographic image into useful parts (plant) and other parts (background), and stores and compresses only the useful part. The algorithm is as follows : I. Mask to get the plant information for diagnosis from a photographic image; 2. Delete the background; 3. Compress and store the image of only the plant image. We wrote a program to recognize and to mask the plants based on HSI (Hue, Saturation, Intensity). The program covers not only green vegetables, but also fruits. Furthermore, the program was investigated in combination with existing image compression techniques (for example, tiff and tga). We achieved a compression rate of about 45% compared with original photographs. We expect the compression rate to be increased in the future by optimizing the HSI parameters.

DOI： 10.2525/jshita.11.267

CiNii Books

researchmap

Other Link： https://jlc.jst.go.jp/DN/JALC/00057773599?from=CiNii

Language：Japanese   Publisher：JAPANESE SOCIETY OF AGRICULTURAL, BIOLOGICAL AND ENVIRONMENTAL ENGINEERS AND SCIENTISTS  

In greenhouse production, computer support systems are being introduced to control the environmental conditions for automation. Furthermore, many robots were studied for automation in agricultural fields. Harvesting robots have been studied in particular. For the automatic robot control, the recognizing system for the positions of fruits and flowers is important. In our laboratory, a 3-dimensional visual sensor system was developed to recognize the direction of strawberry fruit.<BR>To support the movement of the gantry system, a database considering daily changes in the fruit growth has been constructed. This database contains flowers, white unripe fruits, green unripe fruits, mature fruits, however, maturity step, fruit shape, color and 3D coordinates, therefore it can perform shipment predictions.<BR>The previous system could not recognize very small fruits were colored white and green. Using the HSI color model (hue, saturation, intensity), it is possible that very small fruits can be successfully recognized.<BR>In this paper, we developed flower and fruit database to determined these small fruits. We also made a recognition system for flowers and small fruits.<BR>Thus, the database developed here enables us to plan for harvesting fruits by robot, and would be an effective increase in the operational efficiency of harvesting.

DOI： 10.2525/jshita.10.145

CiNii Books

researchmap

Other Link： https://jlc.jst.go.jp/DN/JALC/00055277839?from=CiNii

researchmap

researchmap

researchmap

researchmap

DOI： 10.2525/jshita.10.145

researchmap

Language：Japanese   Publisher：JAPANESE SOCIETY OF AGRICULTURAL, BIOLOGICAL AND ENVIRONMENTAL ENGINEERS AND SCIENTISTS  

In greenhouse production, computer support systems are being introduced to control the environmental conditions for automation. Furthermore, many robots were studied for automation in agricultural fields. Harvesting robots have been studied in particular. For the automatic robot control, the recognizing system for the positions of fruits and flowers is important. In our laboratory, a 3-dimensional visual sensor system was developed to recognize the direction of strawberry fruit.<BR>To support the movement of the gantry system, a database considering daily changes in the fruit growth has been constructed. This database contains flowers, white unripe fruits, green unripe fruits, mature fruits, however, maturity step, fruit shape, color and 3D coordinates, therefore it can perform shipment predictions.<BR>The previous system could not recognize very small fruits were colored white and green. Using the HSI color model (hue, saturation, intensity), it is possible that very small fruits can be successfully recognized.<BR>In this paper, we developed flower and fruit database to determined these small fruits. We also made a recognition system for flowers and small fruits.<BR>Thus, the database developed here enables us to plan for harvesting fruits by robot, and would be an effective increase in the operational efficiency of harvesting.

DOI： 10.2525/jshita.10.145

CiNii Books

researchmap

Other Link： https://jlc.jst.go.jp/DN/JALC/00055277839?from=CiNii

Language：Japanese   Publisher：Japanese Society of Agricultural Informatics  

In the present study, the authors constructed a support system using virtual reality (VR) for plant factory design. To make and simulate a growth model, it is important to consider light conditions and plant arrangement during cultivation. Muskmelon plants were used as a growth model, and heliotropism was used as a characteristic of growth.<br>The system was composed of three units. The first was a CAD designed greenhouse. The second was a unit analyzing sunlight incidence in the greenhouse and the growth of muskmelon plants. The third was a VR that visualized a greenhouse and a plant object.<br>The authors tried to create muskmelon plant objects to confirm the validity of this simulation using the total number of leaves of a muskmelon plant and the light intensity as parameters. From these experiments, it was possible to recreate real shape of muskmelon plant objects in three dimensions. This system also showed that VR was effective to develop a sensuous easy to-understand system.

DOI： 10.3173/air.6.95

CiNii Books

researchmap

Other Link： https://jlc.jst.go.jp/DN/JALC/00049986099?from=CiNii

DOI： 10.2525/jshita.9.132

researchmap

DOI： 10.2525/jshita.9.132

researchmap

DOI： 10.2525/jshita.9.132

researchmap

Language：Japanese   Publisher：Japanese Society of Agricultural Informatics  

In the present study, the authors constructed a support system using virtual reality (VR) for plant factory design. To make and simulate a growth model, it is important to consider light conditions and plant arrangement during cultivation. Muskmelon plants were used as a growth model, and heliotropism was used as a characteristic of growth.<br>The system was composed of three units. The first was a CAD designed greenhouse. The second was a unit analyzing sunlight incidence in the greenhouse and the growth of muskmelon plants. The third was a VR that visualized a greenhouse and a plant object.<br>The authors tried to create muskmelon plant objects to confirm the validity of this simulation using the total number of leaves of a muskmelon plant and the light intensity as parameters. From these experiments, it was possible to recreate real shape of muskmelon plant objects in three dimensions. This system also showed that VR was effective to develop a sensuous easy to-understand system.

DOI： 10.3173/air.6.95

CiNii Books

researchmap

Other Link： https://jlc.jst.go.jp/DN/JALC/00049986099?from=CiNii

Language：Japanese   Publisher：Japanese Society of Agricultural Informatics  

In the present study, the authors constructed a support system using virtual reality (VR) for plant factory design. To make and simulate a growth model, it is important to consider light conditions and plant arrangement during cultivation. Muskmelon plants were used as a growth model, and heliotropism was used as a characteristic of growth.<br>The system was composed of three units. The first was a CAD designed greenhouse. The second was a unit analyzing sunlight incidence in the greenhouse and the growth of muskmelon plants. The third was a VR that visualized a greenhouse and a plant object.<br>The authors tried to create muskmelon plant objects to confirm the validity of this simulation using the total number of leaves of a muskmelon plant and the light intensity as parameters. From these experiments, it was possible to recreate real shape of muskmelon plant objects in three dimensions. This system also showed that VR was effective to develop a sensuous easy to-understand system.

DOI： 10.3173/air.6.95

CiNii Books

researchmap

Other Link： https://jlc.jst.go.jp/DN/JALC/00049986099?from=CiNii

Language：Japanese  

CiNii Books

researchmap

Language：English   Publisher：PERGAMON-ELSEVIER SCIENCE LTD  

For the optimization of long-term plant growth in hydroponics, this paper proposes a hierarchical intelligent control system consisting of an expert system and a hybrid system based on genetic algorithms and neural networks. These two control systems are used appropriately, depending on the plant growth. The plant growth is controlled by the nutrient concentration of the solution. The expert system was used for determining the appropriate setpoints of nutrient concentration through the whole of the growth stages, and the hybrid system for determining the optimal setpoints of nutrient concentration which maximize TLL/SD (TLL: Total leaf length, SD: Stem diameter) only during the initial growth (seedling) stage. In the hybrid system, TLL/SD as affected by nutrient concentration was first identified using neural networks and then the optimal value was determined through simulation of the identified model using genetic algorithms. The setpoints from the expert system were almost similar to those used by a skilled grower. Also, the setpoints from the hybrid system increased the TLL/SD. Thus, this intelligent control technique allowed the optimization of both long-term and short-term plant growth to be realized. This shows that this control technique is suitable for the optimization of such complex and long-term processes as the plant-cultivation process.

DOI： 10.1016/0967-0661(96)00068-8

Web of Science

researchmap

Language：Japanese   Publisher：JAPANESE SOCIETY OF AGRICULTURAL, BIOLOGICAL AND ENVIRONMENTAL ENGINEERS AND SCIENTISTS  

We studied high speed detection of shape characteristics from range image for virtual plant factory. The range image was measured using a laser range finder. In this application, we used a laser sensor that was more wide ranged than that used in previous study, because we measured larger fruits. We made a 3-dimensional model of the fruits that was constructed by a plane represented by polygons.<BR>We made an algorithm for real time processing to find the characteristic points of the polygons. This algorithm had a parameter to cope with different shapes of plants, and it was decided based on the type of plant. In this study, we found the reasonable parameters to construct the polyhedron. The surface of the polyhedron was just like that of the fruits. Processing time of the polyhedron was usually about 2-5 sec. and it was less than 10 sec. even on the fruits with complex shapes. This algorithm was so fast that we could use it for real time operations.

DOI： 10.2525/jshita.8.43

researchmap

DOI： 10.2525/jshita.8.43

researchmap

Language：Japanese   Publisher：JAPANESE SOCIETY OF AGRICULTURAL, BIOLOGICAL AND ENVIRONMENTAL ENGINEERS AND SCIENTISTS  

We studied high speed detection of shape characteristics from range image for virtual plant factory. The range image was measured using a laser range finder. In this application, we used a laser sensor that was more wide ranged than that used in previous study, because we measured larger fruits. We made a 3-dimensional model of the fruits that was constructed by a plane represented by polygons.<BR>We made an algorithm for real time processing to find the characteristic points of the polygons. This algorithm had a parameter to cope with different shapes of plants, and it was decided based on the type of plant. In this study, we found the reasonable parameters to construct the polyhedron. The surface of the polyhedron was just like that of the fruits. Processing time of the polyhedron was usually about 2-5 sec. and it was less than 10 sec. even on the fruits with complex shapes. This algorithm was so fast that we could use it for real time operations.

DOI： 10.2525/jshita.8.43

researchmap

Language：Japanese   Publisher：JAPANESE SOCIETY OF AGRICULTURAL, BIOLOGICAL AND ENVIRONMENTAL ENGINEERS AND SCIENTISTS  

When we think about automation in a plant growth factory, development of intelligent robots is expected. The vision of intelligent robots and the recognition using this sight require the study of a recognition system based on artificial intelligence.<BR>In this project we examined a recognition system using 3-Dimensional range image data processed by a neural network. Especially, we investigated how to make good input for a neural network from 3-D data. This input should contain maximal information with as small input-data as possible.<BR>In this study, we examined orange and eggplant. Input to the neural network were 64 vector lengths from the center of the fruits to the surface. Neural network was trained using the back propagation rule. Hidden layer neuron number and output neuron number were 2. Desired was output 1-0 for the eggplant and 0-1 for the orange. The number of training examples was 25 both in orange and eggplant. Number of interations needed to train the neural network was 10, 000. Verification of the performance of the recognition showed very well results. The recognition system was able to distinguish an orange from an eggplant with great certainty.<BR>This system was intended to recognize round objects. Improvement of algorithm for recognition of long and curved objects like cucumber and uneven surfaces like pimento is the next step. Further, based on the vector lengths, we are developing a recognition system for cracks at the fruit surface.

DOI： 10.2525/jshita.8.49

CiNii Books

researchmap

Language：Japanese   Publisher：JAPANESE SOCIETY OF AGRICULTURAL, BIOLOGICAL AND ENVIRONMENTAL ENGINEERS AND SCIENTISTS  

When we think about automation in a plant growth factory, development of intelligent robots is expected. The vision of intelligent robots and the recognition using this sight require the study of a recognition system based on artificial intelligence.<BR>In this project we examined a recognition system using 3-Dimensional range image data processed by a neural network. Especially, we investigated how to make good input for a neural network from 3-D data. This input should contain maximal information with as small input-data as possible.<BR>In this study, we examined orange and eggplant. Input to the neural network were 64 vector lengths from the center of the fruits to the surface. Neural network was trained using the back propagation rule. Hidden layer neuron number and output neuron number were 2. Desired was output 1-0 for the eggplant and 0-1 for the orange. The number of training examples was 25 both in orange and eggplant. Number of interations needed to train the neural network was 10, 000. Verification of the performance of the recognition showed very well results. The recognition system was able to distinguish an orange from an eggplant with great certainty.<BR>This system was intended to recognize round objects. Improvement of algorithm for recognition of long and curved objects like cucumber and uneven surfaces like pimento is the next step. Further, based on the vector lengths, we are developing a recognition system for cracks at the fruit surface.

DOI： 10.2525/jshita.8.49

CiNii Books

researchmap

Language：Japanese   Publisher：JAPANESE SOCIETY OF AGRICULTURAL, BIOLOGICAL AND ENVIRONMENTAL ENGINEERS AND SCIENTISTS  

When we think about automation in a plant growth factory, development of intelligent robots is expected. The vision of intelligent robots and the recognition using this sight require the study of a recognition system based on artificial intelligence.<BR>In this project we examined a recognition system using 3-Dimensional range image data processed by a neural network. Especially, we investigated how to make good input for a neural network from 3-D data. This input should contain maximal information with as small input-data as possible.<BR>In this study, we examined orange and eggplant. Input to the neural network were 64 vector lengths from the center of the fruits to the surface. Neural network was trained using the back propagation rule. Hidden layer neuron number and output neuron number were 2. Desired was output 1-0 for the eggplant and 0-1 for the orange. The number of training examples was 25 both in orange and eggplant. Number of interations needed to train the neural network was 10, 000. Verification of the performance of the recognition showed very well results. The recognition system was able to distinguish an orange from an eggplant with great certainty.<BR>This system was intended to recognize round objects. Improvement of algorithm for recognition of long and curved objects like cucumber and uneven surfaces like pimento is the next step. Further, based on the vector lengths, we are developing a recognition system for cracks at the fruit surface.

DOI： 10.2525/jshita.8.49

CiNii Books

researchmap

DOI： 10.2525/jshita.7.110

researchmap

researchmap

researchmap

Language：Japanese   Publisher：JAPANESE SOCIETY OF AGRICULTURAL, BIOLOGICAL AND ENVIRONMENTAL ENGINEERS AND SCIENTISTS  

In this study, we made a three-dimensional laser-measurement system for crops. This system composed of two units. One is a laser distance meter for measuring <I>z</I> axis, which apply the laser of 670 nm wave length, and has the resolving power of 0.01 μm. The other is <I>x</I>-<I>y</I> axis robot for measuring the position of <I>x</I> and <I>y</I>, whose accuracy is 0.01 mm. This system is available for the measurement of 40 mm length (<I>x</I> axis), 40 mm width (<I>y</I> axis) and 20 mm height (<I>z</I> axis). <BR>By using this system, we measured the three-dimensional shapes of flowers and leaves under 20 mm length. These data were inverted to neutral file format (NFF) data which had the information of <I>x</I>-<I>y</I>-<I>z</I> positions and polygons which was characterized by triangle points and used for the construction plane. The NFF data was processed by a workstation with graphics system which has 84 K polygon/sec. We could measure and construct the three-dimensional image of such a complex shape as flowers and leaves, with successful results.

DOI： 10.2525/jshita.7.103

CiNii Books

researchmap

researchmap

researchmap

Language：English   Publisher：INTERNATIONAL SOCIETY HORTICULTURAL SCIENCE  

Growth inhibition and physiological disorder of crops frequently appear in plants cultivated under hydroponic conditions. In order to automate a cultivation system, it is essential to develop a diagnosis system for detecting the physiological status of crops in artificial intelligence by using computers. Image analysis was incorporated into a program for physiological diagnosis. The program contains an expert system that was developed from routine cultivation practices and a physiological diagnosis system that exerts physiological reasoning by using image analysis.
The program was tested in the cultivation of tomato plants (Lycopersicon esculentum Mill.) by using hydroponic culture in greenhouses. images of fruits of tomato plants were taken by using a video camera connected to a computer. Growth rates, shapes and colors were analyzed from the images by the computer. Growth inhibition in leaves and stems was identified, and blossom-end rot in fruits was detected from the image analysis. When the physiological diagnosis system was combined with the expert system in artificial intelligence, growth inhibition in stems and blossom-end rot in fruits could be avoided in hydroponic culture.

Web of Science

researchmap

Language：Japanese   Publisher：JAPANESE SOCIETY OF AGRICULTURAL, BIOLOGICAL AND ENVIRONMENTAL ENGINEERS AND SCIENTISTS  

In this study, we made a three-dimensional laser-measurement system for crops. This system composed of two units. One is a laser distance meter for measuring <I>z</I> axis, which apply the laser of 670 nm wave length, and has the resolving power of 0.01 μm. The other is <I>x</I>-<I>y</I> axis robot for measuring the position of <I>x</I> and <I>y</I>, whose accuracy is 0.01 mm. This system is available for the measurement of 40 mm length (<I>x</I> axis), 40 mm width (<I>y</I> axis) and 20 mm height (<I>z</I> axis). <BR>By using this system, we measured the three-dimensional shapes of flowers and leaves under 20 mm length. These data were inverted to neutral file format (NFF) data which had the information of <I>x</I>-<I>y</I>-<I>z</I> positions and polygons which was characterized by triangle points and used for the construction plane. The NFF data was processed by a workstation with graphics system which has 84 K polygon/sec. We could measure and construct the three-dimensional image of such a complex shape as flowers and leaves, with successful results.

DOI： 10.2525/jshita.7.103

CiNii Books

researchmap

Language：Japanese   Publisher：JAPANESE SOCIETY OF AGRICULTURAL, BIOLOGICAL AND ENVIRONMENTAL ENGINEERS AND SCIENTISTS  

In this study, we made a three-dimensional laser-measurement system for crops. This system composed of two units. One is a laser distance meter for measuring <I>z</I> axis, which apply the laser of 670 nm wave length, and has the resolving power of 0.01 μm. The other is <I>x</I>-<I>y</I> axis robot for measuring the position of <I>x</I> and <I>y</I>, whose accuracy is 0.01 mm. This system is available for the measurement of 40 mm length (<I>x</I> axis), 40 mm width (<I>y</I> axis) and 20 mm height (<I>z</I> axis). <BR>By using this system, we measured the three-dimensional shapes of flowers and leaves under 20 mm length. These data were inverted to neutral file format (NFF) data which had the information of <I>x</I>-<I>y</I>-<I>z</I> positions and polygons which was characterized by triangle points and used for the construction plane. The NFF data was processed by a workstation with graphics system which has 84 K polygon/sec. We could measure and construct the three-dimensional image of such a complex shape as flowers and leaves, with successful results.

DOI： 10.2525/jshita.7.103

CiNii Books

researchmap

Language：Japanese   Publisher：JAPANESE SOCIETY OF AGRICULTURAL, BIOLOGICAL AND ENVIRONMENTAL ENGINEERS AND SCIENTISTS  

Virtual reality (VR) is applied to the animation of shadow change as effected by light condition in plant factory. To study VR, we used work station which have a three-dimensional graphic system and three functions of shading, rendering and animation. Shading function was to add shade of structure, rendering function was to display shading object, animation function was to show moving object made by rendering.<BR>We made three types of animation. First is the view of plant factory using the rendering function, second is the animation of movement of view point using animation function, third is the animation of moving shadow based on the sun and artificial light. We showed the animation of three structures based on VR. It took 48 hours to make the animation of 200 frames.

DOI： 10.2525/jshita.7.110

CiNii Books

researchmap

Language：Japanese   Publisher：JAPANESE SOCIETY OF AGRICULTURAL, BIOLOGICAL AND ENVIRONMENTAL ENGINEERS AND SCIENTISTS  

Virtual reality (VR) is applied to the animation of shadow change as effected by light condition in plant factory. To study VR, we used work station which have a three-dimensional graphic system and three functions of shading, rendering and animation. Shading function was to add shade of structure, rendering function was to display shading object, animation function was to show moving object made by rendering.<BR>We made three types of animation. First is the view of plant factory using the rendering function, second is the animation of movement of view point using animation function, third is the animation of moving shadow based on the sun and artificial light. We showed the animation of three structures based on VR. It took 48 hours to make the animation of 200 frames.

DOI： 10.2525/jshita.7.110

CiNii Books

researchmap

researchmap

researchmap

researchmap

DOI： 10.2525/ecb1963.30.185

researchmap

Language：Japanese   Publisher：日本生物環境調節学会  

DOI： 10.2525/ecb1963.30.185

CiNii Books

researchmap

DOI： 10.2525/ecb1963.30.185

researchmap

researchmap

researchmap

researchmap

researchmap

Language：English   Publishing type：Research paper, summary (international conference)   Publisher：AMER SOC PLANT PHYSIOLOGISTS  

Web of Science

researchmap

Language：Japanese   Publisher：日本生物環境調節学会  

DOI： 10.2525/ecb1963.29.51

CiNii Books

researchmap

Language：Japanese   Publisher：日本生物環境調節学会  

CiNii Books

researchmap