Shunsuke Aoki

Security and Privacy for Cooperative Autonomous Vehicles

Grant No.：JPMJPR2131

Researcher

Shunsuke Aoki

Outline

Connected and Autonomous Vehicles have a variety of IoT sensors and each vehicle uses the data for its own driving. To improve road safety while satisfying the security and privacy concerns, this research project studies the driving data for autonomous vehicles and develops security and privacy frameworks, techniques, and applications. Such frameworks and applications enable the secure cooperation among multiple vehicles, infrastructure IoT sensors, and remote users.

Kai Kunze

An Accessibility Assessment Toolkit for Inclusive IoT Design using Onbody Sensing

Grant No.：JPMJPR2132

Researcher

Kai Kunze

Outline

Inclusive Design and Accessibility are two core concepts emphasised in nearly all 17 of the UN’s Sustainable Development Goals. People who do not fit the idea of an “average user” can benefit immensely from the Internet of Things. However, currently accessibility in IoT is left to the developers and engineers of the individual IoT services and systems. There is no architecture or framework support for Inclusive IoT Design. This project will build an Open Accessibility Assessment Toolkit for Inclusive IoT Design that will provide a foundation for evaluating diverse IoT services in terms of user-perceived accessibility using on-body sensing. It provides the first steps to an Inclusive IoT architecture enabling an in-situ, dynamic system reconfiguration.

Shinichi Shirakawa

Automatic Customization of Machine Learning for IoT Security

Grant No.：JPMJPR2133

Researcher

Shinichi Shirakawa

Outline

Although IoT technology is attracted much attention, cyber-attacks that exploit the vulnerabilities of IoT devices are also increasing. Therefore, improving IoT security is an urgent issue. This research project aims to improve machine learning-based IoT security by automatically customizing features and model structures depending on the types and applications of IoT devices. In particular, this project develops efficient techniques for automatic customization of machine learning by cooperating with the data observed by multiple IoT devices.

Yuta Sugiura

Medical-engineering cooperation through medical system design platform

Grant No.：JPMJPR2134

Researcher

Yuta Sugiura

Outline

In this research, we aim to create outcomes through the integration of informatics and medicine. We focus on orthopedic diseases and aim to understand the principle of disease estimation and to develop various screening systems. In order to create these outcomes, we will build a platform to support the design of medical screening systems. Through this research, we will be able to establish medical screening methods that take into account regional and national disparities. In addition, the estimation of diseases in the daily environment will lead to the prevention of severe diseases.

Masahiro Toyoura

Factorization of anonymous sensing data into features of humans, actions, and objects

Grant No.：JPMJPR2135

Researcher

Masahiro Toyoura

Outline

There is a growing global trend to prevent the acquisition of identifiable personal information. We aim to realize accurate action recognition and data tracking for the same person, even from anonymous sensing data, without facial images or personal matching. By factorizing sensing data into the features of humans, actions, and objects, we can eliminate the influence of each other on the recognition. This work contributes to the construction of anonymous big data that enables advanced data gathering, distribution, storage, and analysis.

Yorie Nakahira

Control and Adaptation with Provable Safety and Resilience Inspired from the Human Sensorimotor System

Grant No.：JPMJPR2136

Researcher

Yorie Nakahira

Outline

This research aims to develop control and adaptation methods with provable safety and resilience. We will first study how to design the control/adaptation policies with provable performance guarantees in obstacle avoidance, robustness, fault tolerance, and adaptability. To further improve the performance and de-constrain fundamental limits, we will study how the human sensorimotor control achieves this via Diversity-enabled Sweet Spots and adapt them to autonomous systems. The results will be transferred to miniature prototypes of autonomous vehicles and drones. Ultimately, we expect the proposed research to push the boundary of provable safety and resilience of autonomous vehicles/drones closer to the wild.

Yu Nakayama

Data Reduction for Sustainable IoT

Grant No.：JPMJPR2137

Researcher

Yu Nakayama

Outline

The recent advances in communication and AI technologies have led to the drastic increase of IoT devices and digital data The collection and processing of large amounts of data poses challenges such as increased facility costs, power consumption, and user privacy. The goal of this research is sustainable IoT by reducing the size and spatio-temporal density of data through an integrated approach of data processing and communication.

Hiroki Watanabe

Establishing Security Platform in Hearable Computing

Grant No.：JPMJPR2138

Researcher

Hiroki Watanabe

Outline

In a society where earphone-type computers (hearables) are always worn, users will always receive information through the hearables and act on it. Therefore, there is a possibility of manipulating the user’s behavior by attacking the hearables or changing the user’s auditory characteristics by constantly presenting information. This project clarifies the threats of always wearing hearables and develops countermeasure technologies to establish a security platform in hearable computing.