Recent technological advances in manufacturing allow for high-speed mass production and more manufacturers to utilize online inspection machines, such as cameras that detect defective products, to enhance their production ability. However, online inspection machines are still in the development stage and might cause misclassifications, which can result in unnecessary investment or potential loss in manufacturers' reliability. The objective of this study is to build a more precise defect detection system to discriminate between non-defective products and defective products. Previous studies utilized filtering methods such as feature extraction in relation to a filtering window before classification to enhance precision. Our study adopted a different approach in classification process to further increase its precision. We designed a preprocessing process and a feature extracting process based on a variable importance from Random Forest, and a classification process composed of our newly developed ensemble classifiers. As a result, we succeeded in constructing a defect detection system that performs classification with over 90% accuracy, which is more precise than the previous system. Making the most of AdaBoost's algorithm to overcome the difficulty in the classification resulted in an improvement in the system's precision.
We use paired comparison to rank items. If the number of items is large, we have to compare them many times. In such a case, implementation of an experiment becomes infeasible because of the expense and time required for each experimental run. In addition, evaluation criteria vary from person to person. Therefore, we need experimental designs to take these factors into account. In this paper, we discuss the experimental designs of paired comparisons in incomplete designs. We compare three pairing rules, namely, slide pairing, fold pairing, and adjacent pairing. As a result, we find that adjacent pairing is inferior to slide pairing and fold pairing. It is necessary to select slide pairing or fold pairing based on the number of comparisons. However, after a threshold number of comparisons, slide pairing and fold pairing do not always yield the best results. These results clarify the recommended number of comparisons and the best pairing rules. We believe that the results can be used by people who use paired comparison in practice.
At hospitals, invasive medical techniques such as insertion of a central venous catheter are basic and common techniques for medical doctors. Since invasive techniques have impact on patient's body, standardization for quality assurance through prevention of any problems is important. In activities of standardization, not only preparation of operating procedure but also observation of process with operating procedure are required. In this paper, “observation of processes” is defined as an action to follow processes with operating procedures accurately. The purpose of this study is to develop a practical method for observation of processes with operation procedures and demonstrate efficiency of observation for invasive medical techniques. In this paper, we develop a method to observe processes using checklists in invasive medical techniques. In this method, processes are observed practically through implementation of checklists in daily operation of invasive medical techniques. In a verification for central venous catheter insertion process in hospital A, higher rate of observation have been achieved and improved outcomes of process performance have implied.
The school-age period is significant in children's growth process. Children lacking self-management ability require regular support from their surroundings. In particular, educational institutions play an important part, and a health management system based on periodic medical examination is required. In this study, to develop a health management system, a health management process was visualized. In the next step, we developed a problem-finding method. Based on transition in height and weight, we developed a logic for early detection of children with a tendency toward short stature, overweight, and underweight. Additionally, we designed a support tool integrating this logic. The validity and feasibility were confirmed by a specialist by applying this method to actual body measurement data. Finally, we developed a structure of knowledge for cause analysis. For further study, feedback to children and their parents is required to enhance their self-care ability. In addition, it is possible to develop this into a regional health care system for individuals other than children by applying the methodology of regional cooperation.