In this paper, we develop a computerized human post-mortem identification system by using chest biometrics feature. The main purpose is to identify an unknown person after death. An unknown death body is identified by comparing the chest CT image after death with the X-ray images before death stored in a database to find the highest similarity. The proposed system consists of four main processes: pre-processing, boundary extraction, feature extraction, and similarity calculation and ranking results. All the images are firstly enhanced using Contrast Limited Adaptive Histogram Equalization (CLAHE), and then ribs boundaries are extracted using morphological erosion. After that, the features are extracted using Discrete Fourier Transform (DFT). We use the Euclidean distance to calculate similarity between those features, and then ranking is performed based on the resulted distances. Finally, the system retrieves the ante-mortem X-ray images that are similar to the query image of post-mortem CT image of a death person. Experiments are conducted on dataset collected from the Faculty of Medicine, University of Miyazaki, and our experimental results are compared with the best result of the existing system under the same conditions. From the comparison, our proposed system performs best and gives the accuracy of 74.07%.

View full abstract

In order to deal with the recent serious problems of drug resistance in conjunction with antimicrobials, we developed a web application system called Chans (Charts and antibiogrammaking system) that is capable of analyzing integrated medical data from drug sensitivity tests. We focused on the practical importance of Cross-Resistance Rate (CRR), which is one of the integrated data by Chans. By using clinical data of bacterial species of Pseudomonas aeruginosa (P. aeruginosa) and Escherichia coli (E. coli) donated from a hospital, we will propose a new method of analyzing CRR. In this study, we examined the effectiveness of this method by the Nonmetric Asymmetric Multidimensional Scaling (NAMS). The results of NAMS are visualized on a twodimensional diagram, where the data-to-data distance corresponds to the similarity of the data. The size of the circles on the diagram represents the significance of the data. In the results, the fluoroquinolones (inhibitors of DNA synthesis) appeared in the center of the diagram, while the aminoglycosides, tetracyclines, and macrolides (inhibitors of protein synthesis) appeared in the region to the left of the fluoroquinolones, and the carbapenems, cephems, and penicillins (inhibitors of cell wall synthesis) appeared in the region to the right of the fluoroquinolones. Finally, these placements of CRR were classified with the series of antimicrobials. We also noticed that the size of the circle of each antimicrobial reflects the degree of predominance of cross-resistance. We clarified from these results that the diagram of CRR can be used to visually comprehend transient changes in the cross-resistance of antimicrobials in clinical facilities. This knowledge is indispensable, especially when medical staff employ new antimicrobials. In addition, by comparing the diagrams before and after the prescription of medications in facilities, medical workers can check whether the staff’s treatments were really appropriate or not and optimize the whole process of treatment.

View full abstract

E-commerce has become an important way to sell fresh fruits for E-commerce fruit farmers. However, the picking and delivery cost of fruit farmers especially with large-scale orchards is relatively high in the implementation of E-commerce orders. In order to reduce the cost of picking and delivery fruits and improve the profit of E-commerce fruit farmers, the paper firstly analyzes the process of fruit picking and delivery and identifies main factors that affect the cost of fruit picking and delivery in different situations. Secondly, based on the decision tree, we construct a decision tree model of the picking and delivery costs for farmers, comparing the feasibility of each branch in the decision tree model, and choosing the cheapest and the most feasible plan. Finally, we choose the fruit E-commerce at Zhouyi village in Zhouzhi county as a case, using our decision tree model to analyze the picking and delivery cost and providing the theoretical ground for E-commerce farmers to make plans to pick and deliver fruits. Our work is also helpful for E-commerce fruit farmers to make a quantitative comparison of the costs of different plans of fruit picking and delivery and to increase their profits.

View full abstract

To confront the long-term daily care challenge caused by the shortage of nursing personnel, we are developing a single-body personal care robot for the walking disabled and weak elderly people. In this research, we propose a novel personal care robot with 23 degrees of freedom. Following an introduction to the robot’s mechanical structure and sensor configuration, a motion control method is provided. Additionally, to ensure accurate object manipulation, we present a pose estimation pipeline of important daily necessities for personal care. Ultimately, the proposed motion control and pose estimation methods were verified by experiments.

View full abstract