In this paper, we propose the reefer container monitoring system that not only monitors internal temperature, humidity of reefer container but also tracks the real-time location using GPS. It consists of a tag of information of situation using 433MHz RF transmitter(communication), GPS to track the real-time location and a device using WCDMA/GSM communication to transmit information to the server. We tested by applying the proposed system in reefer containers with yellow melons, melons transported from Korea to Singapore to track the location and check the temperature and the humidity. The result of this test is that there is a temperature difference around 1.7 degree depending on the position of inside of container and maintains the humidity stably about 97%. If we apply this proposed system to agricultural marketing, it is possible to get the time that fruits start to decay and minimize the loss of fruits by decaying during shipping.
In recent years, Container Security Device(CSD) using GPS & GLONASS to improve logistics efficiency are being extensively researched. The purpose of this paper is to examine the performance development antenna usable cargo container security transport. Antenna developed by study were optimized to match logistics environment apply to GPS/GLONASS dual frequency for monitering system. The measure of antenna have confirmation about frequency characteristics each 1575.42MHz, 1602MHz and VSWR is 2:1 measured in return loss-9.54dB. Reliability of this antenna has been verified about GPS/GLONASS through test-operation between the south korea and Russia.
In this paper, we proposed the object classification method using genetic and dynamic random forest consisting of optimal combination of unit tree. The random forest can ensure good generalization performance in combination of large amount of trees by assigning the randomization to the training samples and feature selection, etc. allocated to the decision tree as an ensemble classification model which combines with the unit decision tree based on the bagging. However, the random forest is composed of unit trees randomly, so it can show the excellent classification performance only when the sufficient amounts of trees are combined. There is no quantitative measurement method for the number of trees, and there is no choice but to repeat random tree structure continuously. The proposed algorithm is composed of random forest with a combination of optimal tree while maintaining the generalization performance of random forest. To achieve this, the problem of improving the classification performance was assigned to the optimization problem which found the optimal tree combination. For this end, the genetic algorithm methodology was applied. As a result of experiment, we had found out that the proposed algorithm could improve about 3~5% of classification performance in specific cases like common database and self infrared database compare with the existing random forest. In addition, we had shown that the optimal tree combination was decided at 55~60% level from the maximum trees.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.