AAAI 2017 Spring Symposium

Wellbeing AI: From Machine Learning to Subjectivity Oriented Computing

March 27-29, 2017 (Stanford University)

Description of the symposium
Wellbeing AI is an intelligent information technology that aims to promote psychological wellbeing (i.e. happiness) and maximize human potential. Today’s workplace environment escalates stress, provides unlimited caffeine, distributes nutrition-free “fast” food, and encourages unhealthy sleep behavior. While recent technological advances bring many truly great benefits, there is an opportunity to rethink about the impact of digital technologies on human health and wellbeing. Wellbeing AI provides a way to understand how our digital experience affects our emotions and our quality of life and how to design a better wellbeing system that puts humans at the center.

Recently, Deep Learning and other advanced machine learning technologies has revolutionized in computer vision, speech recognition, and natural language processing and brought promising results in many other areas. Despite this, applying these AI revolutions to human health and wellness problems remains some challenging.

One of the big challenges is to understand human subjective knowledge and design better health & wellbeing systems. We define subjectivity oriented computing is an approach to designing and understanding computations systems by understanding human subjective knowledge.
The Oxford philosopher J.R Lucas mandating that the intelligent being must have self awareness. This symposium discusses the subjective intelligence by learning from human self awareness process.

Today’s wellbeing science (or positive psychology) articulates that positive mental attitudes, including self-awareness can make huge impacts not only in prevention of disease, but also in maximizing human potential. It is now very important to share these scientific findings with AI methodologies for better human centric system design.

For example, we will have the following four technical challenges:

(1)    Representation of subjective knowledge
First, we need to represent the human tacit and subjective health/wellness knowledge in explicit and quantifiable way.  Much of knowledge in well-being science is subjective. For example, fuzzy properties of subjective word embeddings in human health & wellness might be better to be represented with concrete mathematical structures.

(2)    Deep Learning and other quantitative methods for Health & Wellness
Second, we need to explore the advanced machine learning technologies, such as deep learning and other quantitative methods, in health and wellness domains. Right now machine learning research is interested in getting computers to be able to understand data that humans do: images, text, sounds, and so on.  However the focus is going to shift to getting computers to understand things that humans don’t. We need to make a bridge to allow humans to understand these things.

(3)    Models, Reasoning and Inference
Third, the reasoning about data through representations should be understandable and accountable to human. For example, we need to develop powerful tools for understanding what exactly, deep neural networks and other quantitative methods are doing. Not only for increasing accuracy rate of predictions, we need to understand the causality with reliable models, reasoning and inference.

(4)    Better Well-being systems design.
Furthermore, we need to understand the human. While recent technological advances bring many truly great benefits, there is an opportunity to rethink about the impact of these fruits. We need to understand how our AI revolution affects our emotions and our quality of life and how to design a better well being system that puts humans at the center.

This symposium is aimed at sharing latest progress, current challenges and potential applications related with AI health and wellbeing. The evaluation of digital experience and understanding of human health and wellbeing is also welcome.

Scope of Interests
The following topics are scope of our interests, but not limited to;

1. How to quantify our health happiness and well-being.
sleep monitoring, diet monitoring, vital data, diabetes monitoring, running/sport calorie monitoring, personal genome, personal medicine, new type of self-tracking device, portable mobile tools, Health data Collection, Quantified Self tools, experiments, Affective computing, Wearable and cognition, Brain Fitness and Training, Learning enhancement strategies, sleep, dreaming, relaxation, meditation, Yoga, Physiology, Nutrition, Chemicals, Electrical Stimulation (tDCS, rTMS, CES, EEG, neurofeedback)

2. How to analyze the health and wellness data for discovering the new meanings.
Discovery informatics technologies; deep learning, data mining and knowledge modeling for wellness, collective intelligence/ knowledge, life log analysis (e.g., vital data analyses, Twitter–based analysis), data visualization, human computation, etc. ),  biomedical informatics, personal medicine.
Cognitive and Biomedical Modeling;  brain science, brain interface, physiological modeling, biomedical informatics, systems biology, network analysis, mathematical modeling, Disease Dynamics, Personal genome, Gene networks, genetics and lifestyle with Microbiome, health/disease risk.

3. How to design better health and well-being space.
Social data analyses and social relation design, mood analyses, human computer interaction, health care communication system, natural language dialog system, Personal behavior discovery, Kansei, Zone and Creativity ,compassion, calming technology, Kansei engineering, Gamification, Assistive technologies, Ambient Assisted Living (AAL) technology.

4. Applications, platforms and Field Studies
 Medical recommendation system, care support system for aged person, web service for personal wellness, games for health and happiness, life log applications, disease improvement experiment (e.g., metabolic syndrome, diabetes), sleep improvement experiment, Healthcare /Disable support system, community computing platform.

Format of symposium
The symposium is organized by the invited talks, presentations, and posters and interactive demos.

Submission requirements
Interested participants should submit either full papers (8 pages maximum) or extended abstracts (2 pages maximum). Extend abstracts should state your presentation types (long paper (6-8 pages), short paper (1-2 pages), demonstration, or poster presentation) The electronic version of your paper  should be send to
The submission was closed.

Invited speakers
Steve Cole (UCLA, U.S.A)
Christopher Re (Stanford, U.S.A)
Kenji Suzuki (University of Tsukuba, Japan)

Monica Worline (Stanford University)
Michael Nova (Pathway Genomics Inc.)

Session Schedule
 Date Time
March 27
 9:00 - 9:15
 Welcome and Self-introduction  
   9:15 - 9:40  Overview and Censor-based Well-Being The Challenges for Machine Learning and Subjective Computing in Well-being AI (Takashi Kido)
   9:40 - 10:05  Interaction ENRICHME Integration of Ambient Intelligence and Robotics for AAL (Nicola Bellotto)
  10:05 - 10:30   Sensor-based Detection of Invisible Changes in Activities towards Visualizing Disuse Syndrome (Shuya Masuda)
  10:30 - 11:00  Coffee Break  
   11:00 - 11:45  Invited Talk 1 Ameliorating the Labeling Bottleneck with Weak Supervision (Alex Ranter)
   11:45 - 12:30  Invited Talk 2 Not Just a Black Box: Interpretable Deep Learning for Genomics and Beyond (Avanti)
   12:30 - 14:00  Lunch  
   14:00 - 14:45  Invited Talk 3 Using Artificial Intelligence for Cognitive Healthcare and Data Mining (Michael Nova)
   14:45 - 15:30  Invited Talk 4 The Intelligence of Unintelligent Agents:Bots-Integrated Human Coordination in Experimental Social Networks (Hirokazu Shirado)
  15:30 - 16:00  Coffee Break  
   16:00 - 16:25  Interactive Support System for Elderly Persons The interactive robotic system assisting image based dialogue for the purpose of cognitive training of older adults(Hikaru Otaki)
   16:25 - 16:50    The robot facilitating conversation by revoicing keywords learning from active conversations among health old sisters(Tabito Kurosaka)
   16:50 - 17:15    Mutual Acceptance by Sharing Information through Indirect Biofeedback (Madoka Takahara)
   17:15 - 17:30  Taking photos
   17:30 - 18:00  Break  
   18:00 - 19:00  Reception  
March 28
 9:00 - 9:15
   9:15 - 9:40  Interactive Support System for Visual
Visual Impression generation system based on Boids algorithm(Masafumi Ishii)
   9:40 - 10:05  Body Motion for Well-being Health Promotion AI for Full-body Motion Gaming (Takahiro Kusano)
   10:05 - 10:30    The Role of Body Motion Synchrony in Distance Education(Jinhwan Kwon)
  10:30 - 11:00  Coffee Break  
   11:00 - 11:45  Invited Talk 5 Subjectivity-Oriented Computing to Understanding and Empowering Individuals (Kenji Suzuki)
   11:45 - 12:30  Invited Talk 6 Evaluation of Care Skills using First Person Video (FPV) (Atsushi Nakazawa)
   12:30 - 14:00  Lunch  
   14:00 - 14:45  Invited Talk 7 Social Regulation of Human Genome Expression (Steve Cole)
   14:45 - 15:30  Invited Talk 8 TBA (Guido Pusiol)
  15:30 - 16:00  Coffee Break  
   16:00 - 16:25  Mediation Detection for Well-being Brain Functional State Analysis of Mindfulness using Graph Theory and functional Connectivity (Tomoyuki Hiroyasu)
   16:25 - 17:30  Demonstration & Poster (TBA) Kenta Oono
(TBA) Rohan Dixit
   17:30 - 18:00  Break  
   18:00 - 19:00  Plenary Session  
March 29
 9:00 - 9:15
   9:15 - 9:40  Sleep Stage Estimation for Well-being Improving Accuracy of Real-time Sleep Stage Estimation by Considering Personal Sleep Feature and Rapid Change of Sleep Behavior (Tomohiro Harada)
   9:40 - 10:05    Sleep Stage Estimation using heartrate approximate minimum method (Yusuke Tajima)
   10:05 - 10:30  Machine Learning for Well-Being Towards Guideline for Applying Machine Learning into Care Support Systems (Keiki Takadama)
  10:30 - 11:00  Coffee Break  
   11:00 - 11:25  Feeling Analysis for Well-being Loneliness in a Connected World: Analyzing Online Activity and Expressions on Real Life Relationships of Lonely Users(Camille Marie Ruiz)
   11:25 - 11:50  Visualization for Well-being How do huge M&As affect our health? (Tasuo Nakamura)
   11:50 - 12:15    R&D Trend Analysis of Wellbeing AI by using Panoramic View Analytics (Takayoshi Hayashi)
   12:15 - 12:30  Award selection Symposium wrap-up : Summary of New Insights and Questions

Organizing Committee
    Takashi Kido (Rikengenesis, Japan)
    Keiki Takadama (The University of Electro-Communications, Japan)
Programming Committee
    Melanie Swan (DIYgenomics, U.S.A.)
    Katarzyna Wac (Stanford University, U.S.A and University of Geneva, Switzerland)
    Ikuko Eguchi Yairi (Sophia University, Japan)
    Fumiko Kano  (Copenhagen Business School, Denmark)
    Chirag Patel (Stanford University, U.S.A)
    Rui Chen (Stanford University, U.S.A)
    Ryota Kanai (
Araya Brain Imaging, Japan)
    Yoni Donner (Stanford, U.S.A)
    Yutaka Matsuo (University of Tokyo, Japan)
    Eiji Aramaki (Nara Institute of Science and Technology, Japan)
    Pamela Day (Stanford, U.S.A)
    Tomohiro Hoshi (Stanford, U.S.A)
    Miho Otake (Chiba University, Japan)
    Yotam Hineberg  (Stanford, U.S.A)
    Yukiko Shiki (Kansai University, Japan)
    Takashi Maruyama (Stanford, U.S.A)
    Maki Sakamoto (The University of Electro-Communications, Japan)
Advisory committee
    Atul J. Butte (UCSF, U.S.A.)
    Seiji Nishino (Stanford University, U.S.A.)
    Katsunori Shimohara (Doshisha University, Japan)
    Takashi Maeno (Keio University, Japan)

Takashi Kido (Ph.D, Computer Science)
Taito-Ku, Taito, 1-5-1, Tokyo,
Toppan Buioding Higashikan 3F