Toyotani Lab., CIT, Nihon University

  Toyotani Lab., College of Industrial Technology, Nihon University
   I use my corporate experience to conduct research on AI/data science SNS management. This technology is highly versatile, and I am conducting joint research with medical and welfare-related organizations. I also conduct joint research with companies in areas such as marketing and management. It's not always easy, but I value the enjoyment of research.
   At the seminar, all participants collaborate to support the revitalization of the local region at the Narashino Ramen Carnival by designing, building, and operating websites and social media platforms, as well as engaging in marketing and AI programming. Through direct communication with the president and operations manager, proposing solutions independently, and implementing them while receiving feedback, you will gain insights into management's thought processes and practices.
   I also welcome students from other departments, universities, and international graduate schools.

Laboratory Information

Social contribution / Local contribution

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)

WEB/SNS marketing

　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.

Object recognition and passerby counting using AI

The people are blurred out to protect their privacy, while the AI counts the number of pedestrians walking on the street. In addition to people, it can recognize various objects such as cars and bicycles using machine learning. 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.

Currently, we are actually using this AI with the cooperation of MELON LAB.×DANISH LAB. Mimomi Store at Mimomi Station. We have installed and are operating it. This technology makes it possible to automatically count the number of passersby all year round, every hour, by automatically recognizing their age group and gender. To this end, it is possible to make high-precision AI predictions of future sales by analyzing weather, the number of people passing by, and past sales amounts, which will contribute to optimizing store staff and purchasing quantities and solving the SDGs food loss problem. It can also contribute to reducing greenhouse gas emissions associated with disposal and incineration.

Educational interview VR system

　In our laboratory, we are conducting joint research with professors from the School of Medicine to develop next-generation educational systems.

Medical AI system

　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.

Automate visual evaluation by veteran professional engineers using AI after retirement

　For example, this is an example of cracks in concrete, and on-site professionals with extensive experience visually evaluate deterioration. However, there is an issue of age, and I will reach retirement age in a few years. Although it is necessary to pass on the technology, AI machine learning can be said to be optimal. By using machine learning on a huge amount of past evaluation data, AI can instantly give the same evaluation as a veteran.

The figure below shows the locations evaluated by the AI in color, allowing you to see the basis for where the AI was looking. Normal AI is a black box, but this is a new technology that is attracting a lot of attention.

New technology for environmental investigation

　It is necessary to record environmental sounds at work sites, such as in medical welfare facilities and corporate environmental surveys. However, when recording the noise, etc., the contents of other people's conversations are also saved, compromising privacy. To address this issue, we are developing technology that renders conversation content unintelligible by applying processing to the sound recording process.

Medical-engineering collaboration activities

Nihon University is currently focusing on medical-engineering collaboration by leveraging its strengths as a comprehensive university, and the School of Medicine, School of Pharmacy, School of Science and Technology, School of Industrial Engineering, School of Engineering, School of Arts and Sciences, School of Arts, etc. are collaborating to conduct joint research. . The photo shows a report on the results of the Nihon University Special Research, but I am currently the representative of Nihon University's artificial intelligence researcher liaison committee, and this year I am also holding the Medical-Engineering Collaboration Symposium as executive committee chair. .

Crime detection and prevention using AI

Each store is equipped with security cameras, and by integrating AI into these systems, it is possible to automatically detect criminal activities such as shoplifting. The diagram illustrates AI-powered image recognition, where the green circular points indicate locations such as hands, elbows, and shoulders, and their coordinates can be measured in real time. Using these coordinates for motion analysis and modeling makes automatic crime detection achievable.

Monitoring camera footage 24/7 by human eyes is a challenging task. However, with AI automatically detecting incidents, triggering warning sounds, and sending notifications, the workload of store managers and security centers can be significantly reduced and automated. Additionally, AI can detect situations beyond crime, such as someone suddenly feeling unwell, crouching down, or collapsing.
In the future, we aim to integrate AI into security cameras on roads, buildings, and train stations to detect emergencies requiring medical assistance or to prevent crimes before they occur. This would involve playing a siren to deter individuals and simultaneously notifying the police or disaster prevention centers. The goal is to utilize AI to protect and safeguard human lives.

AI navigation for visually impaired people

　Most pedestrian traffic lights are not suitable for visually impaired people. The supply of guide dogs has not kept up with the supply of guide dogs, and people are constantly faced with the risk of falling on steps or stairs. Therefore, we are conducting research on a walking navigation system that utilizes artificial intelligence, with the aim of creating a society where visually impaired people can move freely on their own. The following images show the results of recognizing people and red pedestrian lights.

Step recognition using depth camera

　It seems that many visually impaired people always fall down on steps and get injured, so there is a need to develop technology to recognize steps. In our laboratory, we are conducting research to calculate distance using two cameras on the left and right, and to recognize steps that are dangerous to visually impaired people based on changes in distance to surrounding areas. The photo shows an example of its implementation, with red representing far distances and blue representing close distances.

Utilizing AI for store management

　 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.

SNS marketing practice

　We are currently conducting research on SNS marketing in collaboration with two Japanese confectionery companies. Utilizing the unique ideas of students, we provide support such as taking photos for X and Instagram and creating promotional videos. We also enhance content by analyzing access to our homepage and SNS. By verifying the results and incorporating management opinions, you will gain a management perspective. Even if a large number of customers suddenly arrived at the store, the dough could not be baked right away. It requires a process called fermentation. To this end, advanced prediction calculations using highly accurate AI are required.