Haruhiko Murase

Machine vision based quality evaluation of Iyokan orange fruit using neural networks

It is a common belief that a sweet Iyokan orange fruit is reddish in color, of medium size, with a height to width ratio less than one, and having a glossy surface. However, the criteria are ambiguous and vary from people to people and locations to locations. In this paper, sugar content and acid content of Iyokan orange fruit were evaluated using a machine vision system. Images of 30 Iyokan orange fruits were acquired by a color TV camera. Features representing fruit color, shape, and roughness of fruit surface were extracted from the images. The features included R/G color component ratio, Ferets diameter ratio, and textural features. These features and weight of the fruit were entered to the input layers of neural networks, while sugar content or pH of the fruit was used as the values of the output layers. Several neural networks were found to be able to predict the sugar content or pH from the fruit appearance with a reasonable accuracy.

Practical Application of Methanol-Mediated Mutualistic Symbiosis between Methylobacterium Species and a Roof Greening Moss, Racomitrium japonicum

Bryophytes, or mosses, are considered the most maintenance-free materials for roof greening. Racomitrium species are most often used due to their high tolerance to desiccation. Because they grow slowly, a technology for forcing their growth is desired. We succeeded in the efficient production of R. japonicum in liquid culture. The structure of the microbial community is crucial to stabilize the culture. A culture-independent technique revealed that the cultures contain methylotrophic bacteria. Using yeast cells that fluoresce in the presence of methanol, methanol emission from the moss was confirmed, suggesting that it is an important carbon and energy source for the bacteria. We isolated Methylobacterium species from the liquid culture and studied their characteristics. The isolates were able to strongly promote the growth of some mosses including R. japonicum and seed plants, but the plant-microbe combination was important, since growth promotion was not uniform across species. One of the isolates, strain 22A, was cultivated with R. japonicum in liquid culture and in a field experiment, resulting in strong growth promotion. Mutualistic symbiosis can thus be utilized for industrial moss production.

Finite element inverse analysis using a photosynthetic algorithm.

Abstract The reaction of carbon molecules in the dark reaction of photosynthesis was chosen as a biosystem-derived algorithm (BDA). This study refers to the BDA as the photosynthetic algorithm (PA). The PA utilizes the rules governing the transfer of carbon molecules from one substance into another in the Benson–Calvin cycle and photorespiration reactions. The mechanism of PA is an organized random search biomimetically rationalized by photosynthetic processes. This paper presents the principles of the PA in detail. A finite element inverse analysis was selected as a typical optimization or parameter estimation problem to demonstrate the performance of the PA. The elastic moduli of a finite element model were successfully estimated from predetermined boundary conditions and observed deformation data.

Controlling Circadian Rhythms by Dark-Pulse Perturbations in Arabidopsis thaliana

Plant circadian systems are composed of a large number of self-sustained cellular circadian oscillators. Although the light-dark signal in the natural environment is known to be the most powerful Zeitgeber for the entrainment of cellular oscillators, its effect is too strong to control the plant rhythm into various forms of synchrony. Here, we show that the application of pulse perturbations, i.e., short-term injections of darkness under constant light, provides a novel technique for controlling the synchronized behavior of plant rhythm in Arabidopsis thaliana. By destroying the synchronized cellular activities, circadian singularity was experimentally induced. The present technique is based upon the theory of phase oscillators, which does not require prior knowledge of the detailed dynamics of the plant system but only knowledge of its phase and amplitude responses to the pulse perturbation. Our approach can be applied to diverse problems of controlling biological rhythms in living systems.

Culturable bacteria in hydroponic cultures of moss Racomitrium japonicum and their potential as biofertilizers for moss production

The use of Racomitrium japonicum, a drought resistant bryophyte used for roof-greening, is gradually increasing. However, its utilization is hampered by slow growth rate. Here we isolated culturable bacteria from hydroponic cultivation samples to identify isolates that could promote moss growth. Most of the isolates belonged to Pseudomonas, Rhodococcus, and Duganella species. The isolates were biochemically characterized according to their type of interaction with plants, i.e., production of auxin, siderophores, or hydrogen cyanate, growth in the absence of an added nitrogen source, calcium phosphate solubilization, utilization of sugars, polymers, or aliphatic compounds, and antifungal activity. The isolates were applied to sterile protonemata and non-sterile adult gametophytes of R. japonicum to evaluate their effect on plant growth. Furthermore, we isolated fungi that inhibited moss growth. Our results suggest that the microbial community structure in hydroponic cultures is important to stabilize moss production and the isolates that promote moss growth have potential to be utilized as biofertilizers for moss production.

Inverse Technique for Analysis of Convective Heat Transfer over the Surface of Plant Culture Vessel

A practical method to determine the forced convective heat transfer coefficient over the plant culture vessel was developed. A finite element neural network inverse technique was used to determine parameter values of the Nusselt equation, which, in turn, is needed to calculate the forced convective heat transfer coefficient. The values of the forced convective heat transfer coefficient obtained by the proposed method were then used for the finite element calculation. Thereby, the temperature distribution inside a plant culture vessel was simulated. Agreement was obtained between the finite element results and experimentally measured temperature distribution inside the plant culture vessel.

Growth Monitoring of Green Vegetables Cultured in a Centrifuge Phytotron

Understanding the role of gravity in the biological process of plants is one of most essential aspects in systematic development of Controlled Ecological Life Support or Controlled Bioregenerative Life Support components in space research. A broad parameter database for control and simulation is required for the development of such life support components with higher plants. These instrumentation systems may encompass non-invasive, automated, specific sensors to provide feedback for environmental control and ultimately for system management. Topics include engineering strategies for implementing the speaking plant approach to environmental control of a phytotron based on non-invasive plant growth monitoring system and development of a centrifuge phytotron which will be used to carry out higher plant culture research on the effects of gravity and its absence.

Design of Moss Greening Material for Merapi Disaster Prone Area Using Kansei Engineering

Abstract Merapi is categorized as the most active volcano in Indonesia and most important place of open green space in Yogyakarta, Indonesia. Merapi had erupted from September to October 2010 and destroyed many open green spaces. One of the potential solutions to increase percentage of open green space is the application of greening material in eco-agro-tourism program in Merapi Disaster Prone Area. Greening material is a plant panel consisting of plant and hydroponics media; suitable to be attached in the surroundings of a building. Sphagnum Moss (Sphagnum sp) which is a local biodiversity was used and evaluated as a greening material. The design was developed using Kansei Engineering. Four prototypes of the Sphagnum Moss as greening material were generated as rooftop, canopy, pot and portable garden.

Neural-Genetic Algorithm as Feature Selection Technique for Determining Sunagoke Moss Water Content

Abstract This study investigated the use of machine vision for monitoring water content in Sunagoke moss. The main goal is to predict water content by utilizing machine vision as non-destructive sensing and Neural-Genetic Algorithm as feature selection techniques. Features extracted consisted of 13 colour features, 90 textural features and three morphological features. The specificities of this study was that we were not looking for single feature but several associations of features that may be involved in determining water content of Sunagoke moss. The genetic algorithms successfully managed to select relevant features and the artificial neural network was able to predict water content according to the selected features. We propose neural network based precision irrigation system utilizing this technique for Sunagoke moss production.

Pattern Extraction from Human Preference Reasoning Using Conditional Probability Co-occurrences Matrix of Texture Analysis

A new approach is proposed for extraction of features from human preferences reasoning. Conditional Probability Table (CPT) is a mentality representation to control the reasoning in Bayesian Belief Network (BBN). A software tool was developed using texture analysis with a co-occurrences matrix algorithm. As a case study, it was tested on BBN of moss (Rhacomitrium canescens) produce preferences. The result successfully represented features extracted as specific patterns. It is applicable as a new computational method for reducing many concrete parameters (Dimensionality) and extracting the information from CPT in five textural features. These features are essential as abstractive parameters for designing customized agro-industrial production to provide every consumer with a produce that matches his or her unique preferences.