This paper presents a method for the recognition of fishery types using Deep Convolutional Neural Network. As fishing boat acci-dents are among the highest causes of marine accidents involving death and missing people in Japan, countermeasures are in urgent demand. To prevent collisions between fishing boats and merchant ships, navigators are required to have knowledge in fishery types. This study aims to develop a fishery types recognition system to support navigators in their lookout and to decrease collisions be-tween fishing boats and merchant ships. Experimental results indicate that the trained network has the accuracy of fishery types recognition of 92.38%.

抄録全体を表示

Underactuated manipulators have some passive joints in general, where the number of inputs is less than the degrees of freedom. These systems have complex properties in structure and they have to control a lot of generalized coordinates by few inputs. Here we use MATLAB/Simulink that is software for numerical calculation. It is designed to controllers for underactuated manipulators. In this paper, we try to constitute Real-Time control environments. Then we control a DC-motor using speed control method and position control method with tracking reference signals using trapezoidal drive control. The effectiveness of the proposed method is illustrated through some simulations and experimentations.

抄録全体を表示

The deep hole processing with small diameter is required from manufacturing the dies with high precise for aluminum die-casting for a next-generation automotive. The automatic deep hole processing of small diameter is difficult, caused by difficulty in chip discharge and automatic control of processing conditions according to drill wear state. Currently, the deep hole processing of the die for aluminum die-casing is carrying out by an expert technician manually. When the information obtained by quantifying the expert technician’s skills and techniques for the deep hole processing is characterized and is inputted to an automatic machining system as the processing conditions, the deep hole processing can be performed automatically and effectively. For the purpose of quantifying the above skills and techniques, cutting resistance during deep hole processing by an expert technician is measured, evaluated and characterized based on IoT concept. In this study, in order to characterize the skills and techniques, an intermediate technician and a beginner carry out the same deep hole processing. It was quantitatively clarified that the expert technician carried out the deep hole processing with high processing efficiency. Maximum cutting resistance of the expert technician has excellent potential as the parameter imputed to automatic machining machine for the automation of deep hole processing with small diameter.

抄録全体を表示

Weeds are a problem in most communities and regulations exist regarding their control. However re-growth means that areas may have to be weeded several times a year. The objective of this study was to reduce or eliminate weed re-growth by destroying the root system. It was demonstrated that application of high voltage was effective for root destruction and that selective application was possible.

抄録全体を表示

The review and improvement of dysphagia patient's diet is effective in prevent aspiration pneumonia onset. However, it is qualitative to add a thickener to the liquid foods in the sites of medical and nursing care, based on the subjectivity and experience of dietitians. Thus, a simple measuring machine that quantitatively evaluates the viscous liquid foods was developed. The obtained value is defined as "Thickness Resistance Value (TRV)" and treated as a unit unique to this machine. However, the relationship between TRV and viscosity has not been clarified yet. In this study, this relationship was clarified by using standard liquids for calibrating viscometers and drinking water with thickener added. As a result, the coefficient of variation of TRV was 4% or less when standard liquids for calibrating viscometers was measured. In addition, TRV and viscosity on drinking water with thickener added showed a strong positive correlation. Thus, by introducing the machine to the sites of medical and nursing care, it will be possible to quantitatively evaluate the viscosity of drinking water with thickener added. Therefore, it is expected to improve the quality of life of people with dysphagia and lighten the burden of nursing care.

抄録全体を表示

In order for a machine to operate safely, it is one of the very important factors to quickly and accurately detect an abnormality. A skilled operator can make a diagnosis from the sound produced by the machine. However, constant monitoring by the operator is costly and inefficient. If abnormalities can be detected and maintained at an early stage, it will lead to avoiding serious failures, and cost reduction can be expected by long-term use of the machine. In this study, we proposed a system that uses machine learning to detect abnormalities from the operating sounds of machines. Instead of the conventional judgment method that requires abnormal sounds in advance, a system that judges them only from learning normal sound data is proposed. In order to confirm the effectiveness of the proposed system, we build a machine operation sound generator and conducted experiments by artificially generating abnormal noise of a bearing. We extracted features called Mel-Frequency Cepstrum Coefficient from the sounds, abnormal sounds were detected by using One Class Support Vector Machine. As a result, it was confirmed that the generated abnormal noise was detected, and it was found that the proposed system was effective for abnormality detection.

抄録全体を表示

This paper proposes a new wildlife image recognition method that combines object recognition based on deep learning and motion detection by inter-frame difference. This method makes it possible that such animal images as difficult to detect by object recognition can be detected by motion detection, and vice versa. The experimental results show the detection ratio and hit ratio are 100% and 84%, respectively, for videos including animals. Our achieved results can provide more efficient solutions for the time consuming and costly mitigation approaches to reduce human-wildlife conflicts.

抄録全体を表示

With a rise in the number of people requiring nursing-care in the aging society, the demand for welfare equipments that maintain the quality of nursing-care is increasing. In particular, electric wheelchairs are effective in improving QOL because they support the voluntary movement of users, but the majority of them needs to be operated by movements of upper limbs. Then, the authors developed an operation system of electric wheelchairs that is controlled by voluntary head movements. However, EMG measurement system malfunctioned in low temperature environments, which made it impossible to operate electric wheelchairs. Thus, it is necessary to clarify the cause of this malfunction and ensure the stability of operation. In this study, first, the operation was tested in comfortable environments and low temperature environments (-2<PMV<-3). Next, operation reliability was evaluated based on task success rate and malfunction rate. Consequently, the task success rate and the malfunction rate in low temperature environments were 79% and 12%, which were similar to the results in comfortable environments. Therefore, this system can maintain operation reliability at -2<PMV<-3. Meanwhile, it is indispensable to verify in harsher low temperature than -2<PMV<-3 environments, due to be suggested that the change in muscle fiber conduction velocity was small.

抄録全体を表示