With the popularization of smartphones, SNS, which allows easy message exchange, has become popular. On the other hand, a metaverse has attracted attention recently. In the metaverse, participants interact with each other through avatars in a virtual space. Therefore, if we can show participants the existing SNS space as the metaverse, we can provide participants with more intuitive use cases. This manner is beneficial for elderly people who are unfamiliar with using smartphones. In this paper, we propose LINE metaverse. LINE is the most popular messaging application in Japan. The LINE metaverse is characterized by replacing the bot mechanism used for marketing using SNS with a metaverse agent. In the LINE metaverse, elderly people can exchange messages via avatars on the metaverse.

Hexagonal pattern nets made of polyester monofilament are widely used for fish cages and rockfall prevention due to their durability. Although these nets are manufactured by automatic knitting machines, factory workers constantly monitor the process to prevent abnormalities as it is difficult to distinguish abnormalities. Therefore, it is necessary to automatically, quickly and accurately detect net abnormalities during production. On the other hand, subsequent tension adjusting operations for anomaly clearance must be still performed by factory workers. To prevent mesh abnormalities in knitting machines, therefore, it is not enough just to be able to detect abnormalities with high accuracy; it is also important to obtain feedbacks on the subsequent factory worker’s anomaly clearance operations. This article proposes image features that achieve the requirement and a method for obtaining these features from net images. It further proposes a learning method to identify abnormalities with high accuracy using such images. We shows that the identification accuracy of our method is as high as that of the Convolutional Neural Network (CNN) based method, which is well known by its high performance in detecting anomalies using image data, even when not enough training data is available. In addition, we show that it is easy to estimate which strings need to be adjusted to clear the anomaly by obtaining these proposed image features, without training the classifier. Furthermore, this proposed method was implemented on an actual knitting machine as an experiment, which confirmed that it can detect mesh abnormalities in real-time.

With the growing global demand for marine products, offshore aquaculture, which enables large-scale aquaculture compared to conventional coastal aquaculture, is drawing attention. In offshore aquaculture, the occurrence of red tide due to residual food can be suppressed by the circulation of ocean currents, and the environmental load can be reduced. On the other hand, since the farmed cage is located in a remote area, there are problems such as the cost of transporting food, the storage of a large amount of food, and the management of facilities in the event of a typhoon. In addition, it is especially important to manage the environmental information in the cage in order to understand the health condition of farmed fish in remote areas. If a device that measures water quality, which is one of the environmental information, is left in the sea for a long period of time, dirt such as algae will adhere and the measurement performance will deteriorate. This time, we developed an air pressure control system that allows the water quality sensor in the sea to enter the water only when measuring, and implemented it in the observation device. This observation device enables long-term observation of various water quality data.