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.

In recent years, image inspections have become a useful tool in the early diagnosis of rheumatoid arthritis (RA). However, evaluations in RA ultrasound inspections are visual inspections by doctors, evaluation tends to become somewhat subjective, meaning that it is difficult for less-experienced doctors to make an assessment. In this study, therefore, we propose a system that alleviates the burden on doctors, by automating RA image diagnosis, that is to say an RA image diagnosis support system using ultrasound images. With this system, as it is necessary to automate RA image diagnosis, it is necessary to propose an image classification method with higher classification accuracy. Therefore, in this paper, we propose an image classification method with higher precision, by comparing methods of image classification. We also show our evaluation results. As a result, it is considered that image classification via CNN using automatic extraction images of synovial thickening surrounding areas is effective for image classification of ultrasound images for the purpose of automating RA image diagnosis.

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.

Currently, a communication robot like an AI speaker has become popular as one of consumer services. As realized high functions seen in cooperation of network and home appliances by them, hurdles for the elderly in operating such advanced IT devices are still high. On the other hand, RPA (Robotic Process Automation) attracts attention for productivity improvement of business processing. However, there are few examples that applied RPA to consumer services. It is caused that there is not common sense about an application method of RPA for consumer services. Therefore, if we could define the application method of RPA for consumer services, we could develop consumer services familiar with the elderly. This paper gives some examples of our developed consumer services for the elderly by communication robots after summarizing requirements for applying RPA to consumer services. Then, we inspect the effectiveness of the consumer services based on RPA. Finally, we make clear a RPA basic model for consumer services.