Collaborating Authors

Kyoto Prefecture

Data-crunching AI in Japan predicts one's chances of developing 20 diseases

The Japan Times

Health researchers have put artificial intelligence to work in crunching big data, allowing them to develop technology that can predict the future onset of around 20 diseases so people can make preventative lifestyle changes. The model developed at Hirosaki University and Kyoto University calculates one's probability of developing a disease within three years based on data obtained from voluntary health checkups on about 20,000 people in Japan. If a patient agrees to disclose data on some 20 categories collected during checkups, the model can project the potential development of arteriosclerosis, hypertension, chronic kidney disease, osteoporosis, coronary heart disease and obesity, among other conditions. The team set up two groups of people for each disease -- those whose data suggested they could develop the ailment in the future and a control group -- and crunched their health data to predict whether would will actually develop the disease. "We made correct predictions on whether individuals will develop the diseases within three years with high accuracy," said Yasushi Okuno, professor at Kyoto University's Graduate School of Medicine.

Nintendo suspends Switch game console shipments

The Japan Times

Kyoto – Japan's Nintendo Co. has suspended domestic shipments of its popular Nintendo Switch video game console due to a production delay caused by the coronavirus outbreak, company officials said Wednesday. Nintendo has yet to decide when to resume shipments. The company will continue Nintendo Switch shipments for customers who had placed orders and European and U.S. markets, where sufficient inventories are available. It has also halted domestic shipments of the Switch Lite portable game machine. Nintendo outsources production of the game consoles to plants in China and Vietnam.

Genius triumphs: Japanese mathematician's solution to number theory riddle validated

The Japan Times

KYOTO – A proof by mathematician Shinichi Mochizuki of a major conundrum in number theory that went unresolved for over 30 years has finally been validated, Kyoto University said Friday following a controversy over his method, which was often labeled too novel or complicated to understand. Accepted for publication by the university's Research Institute for Mathematical Sciences was Mochizuki's 600-page proof of the abc conjecture, which provides immediate proofs for many other famous mathematical problems, including Fermat's last theorem, which took almost 350 years to be demonstrated. The abc conjecture, proposed by European mathematicians in 1985, is an equation of three integers a, b, and c composed of different prime numbers, where a b c, and describing the relationship between the product of the prime numbers and c. "There are a number of new notions and it was hard to understand them," Masaki Kashiwara, head of the team that examined the professor's theory, said at a news conference. He proved the abc conjecture with a "totally new, innovative theory," said fellow professor Akio Tamagawa. "His achievement creates a huge impact in the field of number theory."

Kyocera plans health-analysis device based on odor of feces

The Japan Times

Kyocera Corp. has started developing a device to check human health and immunity from the odor of one's stool, aiming to put it into practical use in three years. In collaboration with AuB Inc., a Tokyo-based startup, Kyocera will analyze data from the device, which will be installed in toilet seats. The Kyoto-based electronics giant will create a system that infers the intestinal environment of the user with the aid of artificial intelligence technology and data collected by AuB, according to Kyocera officials. Kyocera will deliver the results to clients through a smartphone application and propose measures to improve diet and other elements of their lives to improve health, the officials said. As part of the development process, AuB will gather stool samples from 29 players of a youth team belonging to Kyoto Sanga F.C., a professional soccer team.



Read the paper to learn more about Kaokore dataset, our motivations in making them, as well as creative usage of it! KaoKore is a novel dataset of face images from Japanese illustrations along with multiple labels for each face, derived from the Collection of Facial Expressions. KaoKore dataset is build based on the Collection of Facial Expressions, which results from an effort by the ROIS-DS Center for Open Data in the Humanities (CODH) that has been publicly available since 2018. It provides a dataset of cropped face images extracted from Japanese artworks publicly available from National Institute of Japanese Literature, Kyoto University Rare Materials Digital Archive and Keio University Media Center from the Late Muromachi Period (16th century) to the Early Edo Period (17th century) to facilitate research into art history, especially the study of artistic style. It also provides corresponding metadata annotated by researchers with domain expertise.

How Japan's forgotten past can stop IoT's dystopian future - Disrupting Japan


Technology is global, but ideas are local. The same IoT technology is being deployed all over the world, but a small Japanese startup might be who helps us make sense of it all. There is amazing work being done in user experience design, but most designers are operating with the contract of keeping users engaged. This is a fundamental shift from the traditional user-centered and functional design approaches. Today we sit down with Kaz Oki, founder of Mui Lab, and we talk about user design can actually improve our lives and help us disengage. We also talk about the challenges of getting VCs to invest in hardware startups, why Kyoto might be Japan's next innovation hub, and what it takes for a startup to successfully spin out of a Japanese company It's a great discussion, and I think you will really enjoy it. Welcome to Disrupting Japan, straight talk from Japan's most successful entrepreneurs. If you're a fan of Disrupting Japan, you know that I have a strong dislike for attempts to make Japan sound too exotic and this goes in both directions. On one side, we have consultants who claim that Japanese business practices are so unique, arcane, and confusing that the only way westerners can possibly understand them is by paying large sums of money to consultants such as themselves. And on the other side, of course, we have people insisting that foreigners can't really understand Japanese anime without a thorough and nuanced knowledge of Japanese language and history. I mean, there are differences, of course, and those differences should be acknowledged and respected, but whether an idea is coming from Japan or America, or Germany, one true measure of the value of that idea is its universality. The most important achievements might emerge out of cultural biases or sensitivities but they address something universally true, something deeply human. Today, we sit down with Kaz Oki of Mui Lab and we're going to talk about Mui's radical rethinking of how we should interact with computers and the different contexts for that interaction. The Mui itself is a tactile and visual user interface that literally fades into the furniture when you're not using it.

Three-dimensional Generative Adversarial Nets for Unsupervised Metal Artifact Reduction Artificial Intelligence

--The reduction of metal artifacts in computed tomography (CT) images, specifically for strong artifacts generated from multiple metal objects, is a challenging issue in medical imaging research. Although there have been some studies on supervised metal artifact reduction through the learning of synthesized artifacts, it is difficult for simulated artifacts to cover the complexity of the real physical phenomena that may be observed in X-ray propagation. In this paper, we introduce metal artifact reduction methods based on an unsupervised volume-to-volume translation learned from clinical CT images. We construct three-dimensional adversarial nets with a regularized loss function designed for metal artifacts from multiple dental fillings. The results of experiments using 915 CT volumes from real patients demonstrate that the proposed framework has an outstanding capacity to reduce strong artifacts and to recover underlying missing voxels, while preserving the anatomical features of soft tissues and tooth structures from the original images. EDICAL procedures such as diagnosis, surgical planning, and radiotherapy can be seriously degraded by the presence of metal artifacts in computed tomography (CT) imaging. Metal objects such as dental fillings, fixation devices, and other electric instruments implanted in patients' bodies inhibit X-ray propagation [1], preventing accurate calculation of the CT values during image reconstruction and yielding dark bands or streak artifacts in the CT images [2][3]. To correct the images, missing CT values for the underlying anatomical features must be compensated at the same time as the artifacts are removed. Although doctors make clinical efforts to manually collect such artifacts, this is a labor-intensive and time-consuming task. M. Nakao and T. Matsuda are with the Graduate School of Informatics, Kyoto University, Y oshida-Honmachi, Sakyo, Kyoto 606-8501, JAP AN; email:

Machine learning constructs map of the brain's neural circuit


According to experts in the field, the brain is considered to be one of the most complex systems in existence. While significant headway has been made to understand how the brain works, researchers tend to generate more questions than answers about this entity. However, the creators of the machine learning model - a team from Kyoto University - believe it has the potential to explain the difference in neuronal computation in different brain regions more clearly. To comprehend the brain, neurologists must look at the neurons that construct it. Our entire world of perception runs across these billions of cells in our head and that is compounded by the exponentially larger number of connections – known as synapses – between them.

Amazing AI generates entire bodies of people who don't exist


A new deep learning algorithm can generate high-resolution, photorealistic images of people -- faces, hair, outfits, and all -- from scratch. The AI-generated models are the most realistic we've encountered, and the tech will soon be licensed out to clothing companies and advertising agencies interested in whipping up photogenic models without paying for lights or a catering budget. At the same time, similar algorithms could be misused to undermine public trust in digital media. The algorithm was developed by DataGrid, a tech company housed on the campus of Japan's Kyoto University, according to a press release. In a video showing off the tech, the AI morphs and poses model after model as their outfits transform, bomber jackets turning into winter coats and dresses melting into graphic tees.

MHIQ Program Seminar Series Healthcare Practice and Survivorship - Reactive and Passive Multisensory Brain-computer Interfaces for Communication or Dementia Biomarkers Elucidation


The presentation will introduce contemporary brain-computer interface (BCI) techniques. Dr Rutkowski will explain auditory, visual, and tactile reactive BCI examples with applications for communication and passive solutions for cognitive-load/dementia biomarker elucidation. He will also discuss future research directions of the so-called neurotechnology applications for healthcare and especially cognitive monitoring solutions. Tomasz Rutkowski received his M.Sc. in Electronics and Ph.D. in Telecommunications and Acoustics from Wroclaw University of Technology, Poland, in 1994 and 2002, respectively. He received postdoctoral training at the Multimedia Laboratory, Kyoto University, and in 2005-2011 he worked as a research scientist at RIKEN Brain Science Institute, Japan.