The image shows AI counting the number of pedestrians walking along the street, using footage from a security camera in front of a store. By utilizing AI to automatically recognize age and gender and count people 24 hours a day, 365 days a year, this data could serve as valuable market information for the AI era.
In addition, we are also developing medical systems that utilize AI for applications in laparoscopic surgery, among others. Currently, we are conducting joint research with School of Medicine, College of Science and Engineering, College of Engineering, College of Humanities and Sciences, and other institutions.
In our laboratory, we are conducting joint research with professors from the School of Medicine to develop next-generation educational systems.
We are collaborating with muujuu.Inc, a company engaged in VTuber production and motion capture technology development, to conduct product development marketing focused on how to utilize new technologies. By presenting fresh ideas unique to students and receiving feedback from the company, we gain a realistic understanding of business perspectives, on-site challenges, and potential issues.
Since VTubers operate in virtual spaces, they cannot physically hold products. However, with Mujuryoku Inc.'s new technology, V-Diver, VTubers can interact with objects in a room, such as holding products, shaking hands with people, or riding vehicles, just as shown in photos. This innovation opens up new possibilities as a marketing tool.
Security cameras are installed in each store, and by introducing AI into these cameras, shoplifting and other criminal acts can be automatically detected. The diagram shows image recognition using AI. The green circles represent hands, elbows, shoulders, etc., and their coordinates can be measured in real time. These coordinates can be used to analyze and model movements, making it possible to automatically detect crime.
It is a lot of work for humans to visually check camera footage 24 hours a day, 365 days a year, but if AI can automatically detect incidents and sound an alarm or send a notification, it will reduce the workload of store managers and security centers and make the process automated.It can also detect not only crimes, but also when someone suddenly becomes ill and crouches down or collapses.
In the future, we would like to use AI to protect people by introducing it into security cameras on roads, in buildings, and at stations, so that when an emergency call is needed or a crime is about to occur, a siren will sound to deter the perpetrator, and at the same time notify the police and disaster prevention center.
In equipment management and risk management, evaluating rust (metal corrosion) is extremely important. Until now, such inspections have been conducted visually by experienced engineers. However, due to issues such as retirement, it has become difficult to pass on these inspection skills to younger engineers in time. As a result, there is a growing need for automatic rust evaluation using machine learning.
The photo below shows a technique called Grad-CAM (Gradient-weighted Class Activation Mapping), which visualizes in red the areas that the AI used for evaluation. This demonstrates that the AI automatically identifies and evaluates rusted areas, even though it was not explicitly instructed where the rust is located.
This is the scene when Toyotani Seminar received an award for contributing to the revitalization of the local area through the Ramen Stamp Rally at the special stage of Narashino Kiratto, Narashino City's largest festival. The mayor of Narashino, the president of the Chamber of Commerce and Industry, the chairman of the executive committee of the Ramen Stamp Rally, President Tokishige, and the seminar leader and vice-seminar leader of the Toyotani Seminar, Toyotani, are lined up.
Nihon University Industrial Engineering students cooperate with local event in Narashino, utilizing SNS and AI (2023/11/08)
Toyotani Seminar, which supported the Ramen Stamp Rally Received a letter of appreciation and commemorative gift from the committee (2022/10/9)
Okubo Mimo Ramen Stamp Rally 2022 Eat, apply, and support the city! (2022/9/3)
Toyotani Laboratory will be hosting the "Okubo/Mitsumi Ramen Stamp Rally" Technical support for operation (2022/06/03)
Ramen restaurant stamp rally in Narashino 14 participating stores (2023/10/27)
At the Ramen Carnival, we utilized the homepage and Twitter (X) to disseminate information and conducted access analysis to investigate the effectiveness. The upper part shows the transition of access numbers for Twitter (X), while the lower part shows the access numbers for the homepage. Initially, the access numbers to the homepage increased for registering in the Ramen Stamp Rally app. However, afterwards, as there was no need to refer to the homepage, the access numbers did not increase. However, through access analysis, it was found that from the posts on Twitter (X), people were not accessing the homepage but directly referring to the SNS of each store.
We are currently collaborating with two traditional Japanese confectionery companies, Oedo Co., Ltd. and Watato Co., Ltd., on SNS marketing activities. Leveraging creative ideas unique to students, we support activities such as photo shoots for X (formerly Twitter) and Instagram, as well as promotional video production.
Both company presidents are personally involved to help communicate the charm of traditional Japanese sweets to younger generations. Videos created by our seminar students are posted by the companies on their platforms, and we receive feedback from the presidents, including insights on viewership and evaluation, which provides valuable exposure to real business perspectives.
In collaboration with [MELON LAB. × DANISH LAB. Mimomi Store (Melon Bread Shop)] located at Mimomi Station, we have started initiatives to utilize AI in management, such as predicting sales and preparation quantities based on past visitor numbers, sales figures, temperature, humidity, weather, and seasons.