ChinaTakahashi_Exploration cyclefinding a better dining experience:a frame...Matsushita Laboratory
The document proposes an exploration cycle to help users find better dining experiences by matching meals to plates. It involves two phases: (1) an expand phase where the computer recommends multiple meal or plate options from a single starting point, and (2) a focused phase where the user selects from these options to refine their search. The system works by converting recipe and plate data into machine-readable formats, linking them by meal names, and then using the linked data to suggest compatible meal-plate pairs in the exploration cycle. The goal is to allow users to discover their own preferences and select optimally matching plates and meals through an interactive, computational process.
This study aims to clarify the composition of story content to help computers understand stories. In story content, the events peculiar to a genre occur intermittently. For example, school and sports festivals appear in school-themed genres. These events can trigger a story because they cause changes in the internal characteristics and relationships between characters, which in turn trigger the progress of the story. If computers can determine the events in a story, they will help understand its composition. Each story-event contains many strongly related words. For example, ``relay'' and ``runner'' appear in sports festival episodes. Therefore, investigating these tendencies is expected to contribute to the estimation of story-events. However, the amount of information obtained from comic texts is limited because they use illustrations and texts in a complementary manner. This makes it difficult for computers to obtain words from comics that characterize a story-event. To address this problem, we focused on the content similarities between comics and light novels. In this study, we estimated story-events in comics using the tendency of story-event words to appear in light novels. The results of this experiment indicate that we can calculate story-events in comics using a dictionary of story-events created by the proposed method.
Unification of Terminology for Accurate Communication among Experts --- Basic...Matsushita Laboratory
This document discusses establishing standardized physiotherapy terminology in Japan through analyzing past national exam questions. The researchers extracted over 1500 terms from questions over the past 5 years and categorized them. They analyzed the terms using morphological and medical dictionary tools to identify duplicate terms and categorize them. The categorization identified terms related to diseases, anatomy, kinesiology, assessments, physiology and other areas. This foundational term collection will help improve accuracy when developing clinical reasoning support systems by reducing variability in terminology.
Visualization of the Relationship Between Lectures and Laboratories Using SSNMFMatsushita Laboratory
This document proposes a method to visualize the fluid relationship between lectures and laboratories using semi-supervised non-negative matrix factorization (SSNMF). It collects data on lectures and graduation theses from laboratories, represents them as multidimensional vectors, and applies SSNMF to output a relationship matrix showing which combination of lectures constitutes specialized fields in laboratories. The method is intended to help students explore lecture and laboratory options by providing quantitative evidence on potential relationships based on each element's characteristics, beyond simple one-to-one comparisons. It is shown to capture the many-to-many relationships between lectures and laboratories when applied to different lecture sets.
The 24th International Conference on Information Integration and Web Intelligence で発表した "Interactive visualization of comic character correlation diagrams for understanding character relationships and personalities" の発表資料です.
ChinaTakahashi_Exploration cyclefinding a better dining experience:a frame...Matsushita Laboratory
The document proposes an exploration cycle to help users find better dining experiences by matching meals to plates. It involves two phases: (1) an expand phase where the computer recommends multiple meal or plate options from a single starting point, and (2) a focused phase where the user selects from these options to refine their search. The system works by converting recipe and plate data into machine-readable formats, linking them by meal names, and then using the linked data to suggest compatible meal-plate pairs in the exploration cycle. The goal is to allow users to discover their own preferences and select optimally matching plates and meals through an interactive, computational process.
This study aims to clarify the composition of story content to help computers understand stories. In story content, the events peculiar to a genre occur intermittently. For example, school and sports festivals appear in school-themed genres. These events can trigger a story because they cause changes in the internal characteristics and relationships between characters, which in turn trigger the progress of the story. If computers can determine the events in a story, they will help understand its composition. Each story-event contains many strongly related words. For example, ``relay'' and ``runner'' appear in sports festival episodes. Therefore, investigating these tendencies is expected to contribute to the estimation of story-events. However, the amount of information obtained from comic texts is limited because they use illustrations and texts in a complementary manner. This makes it difficult for computers to obtain words from comics that characterize a story-event. To address this problem, we focused on the content similarities between comics and light novels. In this study, we estimated story-events in comics using the tendency of story-event words to appear in light novels. The results of this experiment indicate that we can calculate story-events in comics using a dictionary of story-events created by the proposed method.
Unification of Terminology for Accurate Communication among Experts --- Basic...Matsushita Laboratory
This document discusses establishing standardized physiotherapy terminology in Japan through analyzing past national exam questions. The researchers extracted over 1500 terms from questions over the past 5 years and categorized them. They analyzed the terms using morphological and medical dictionary tools to identify duplicate terms and categorize them. The categorization identified terms related to diseases, anatomy, kinesiology, assessments, physiology and other areas. This foundational term collection will help improve accuracy when developing clinical reasoning support systems by reducing variability in terminology.
Visualization of the Relationship Between Lectures and Laboratories Using SSNMFMatsushita Laboratory
This document proposes a method to visualize the fluid relationship between lectures and laboratories using semi-supervised non-negative matrix factorization (SSNMF). It collects data on lectures and graduation theses from laboratories, represents them as multidimensional vectors, and applies SSNMF to output a relationship matrix showing which combination of lectures constitutes specialized fields in laboratories. The method is intended to help students explore lecture and laboratory options by providing quantitative evidence on potential relationships based on each element's characteristics, beyond simple one-to-one comparisons. It is shown to capture the many-to-many relationships between lectures and laboratories when applied to different lecture sets.
The 24th International Conference on Information Integration and Web Intelligence で発表した "Interactive visualization of comic character correlation diagrams for understanding character relationships and personalities" の発表資料です.