This paper focuses on a sleep cycle, and improves the problem which an estimation accuracy of Real-Time Sleep Stage Estimation Method(RSSE) when it estimates a sleep stage on real time. Concretely, the proposed method re-estimates the sleep stage immediately after first sleep cycle since going to bed for the problem which decreases the correct rate of the sleep stage estimated by RSSE as time passes since going to bed. From the human subject experiments, the following implications have been revealed: (1) the correct rate improved by re-estimation in 8 cases out of 9 cases. (2) when the sleep cycle is long, it is possible to calculate the sleep cycle from the same subject's past sleeping information and if it is used, the estimation accuracy is improved for all cases.

This paper focuses on care support knowledge (especially focuses on the sleep related knowledge) and tackles its cognitive bias and humanity aspects from machine learning perspective through discussion of whether machine learning can correct commonly accepted knowledge and provide understandable knowledge in care support domain. For this purpose, this paper starts by introducing our data mining method (based on association rule learning) that can provide only necessary number of understandable knowledge without probabilities even if its accuracy slightly becomes worse, and shows its effectiveness in care plans support systems for aged persons as one of healthcare systems. The experimental result indicates that (1) our method can extract a few simple knowledge as understandable knowledge that clarifies what kinds of activities (e.g., rehabilitation, bathing) in care house contribute to having a deep sleep, but (2) the apriori algorithm as one of major association rule learning methods is hard to provide such knowledge because it needs calculate all combinations of activities executed by aged persons.

Senior isolation is becoming a major social problem in Japan, as a super-aged society where more than a quarter of population is over 65 years old. Many elderly people are living in single-resident homes without family or social support. Even in nursing home, residents stay in their private bedrooms lonely without participating social activities, such as chatting, playing game, watching TV together at a living room, etc. Since social isolation leads to serious consequences such as disuse syndrome, mental depression, suicide etc., main-taining person’s sense of community is very important. But measuring sense of community is difficult because it is a mental process and many kinds of activities and interactions are involved in the process. In this paper, we define Social Activities of Daily Living (SADL) to focus on social activities to enhance the sense of community. We also propose a multimodal sensor based recognition method for SADL, which is implemented in the IoT-based emotion recognition robot for nursing environment. The robot monitors the daily activities and emotions of the residents, estimates the social relationships of the residents, takes care of the residents who are isolated from the community, and reduces their loneliness feelings by forming a good relationship in community.

Long-term observation of changes in Activities of Daily Living (ADL) is important for assisting older people to stay active longer by preventing aging-associated diseases such as disuse syndrome. Previous studies have proposed a number of ways to detect the state of a person using a single type of sensor data. However, for recognizing more complicated state, properly integrating multiple sensor data is essential, but the technology remains a challenge. In addition, previous methods lack abilities to deal with misclassified data unknown at the training phase. In this paper, we propose an architecture for multimodal sensor-based ADL recognition which spontaneously acquires knowledge from data of unknown label type. Evaluation experiments are conducted to test the architecture's abilities to recognize ADL and construct data-driven reactive planning by integrating three types of dataflows, acquire new concepts, and expand existing concepts semi-autonomously and in real time. By adding extension plugins to Fluentd, we expended its functions and developed an extended model, Fluentd++. The results of the evaluation experiments indicate that the architecture is able to achieve the above required functions satisfactorily.

In this AAAI Spring symposium 2018, we discuss cognitive bias and humanity in the context of well-being AI. We define “well-being AI” as an AI research paradigm for promoting psychological well-being and maximizing human potential. The goals of well-being AI are (1) to understand how our digital experience affects our health and our quality of life and (2) to design well-being systems that put humans at the center. The important challenges of this research are how to quantify subjective things such as happiness, personal impressions, and personal values, and how to transform them into scientific representations with corresponding computational methods. One of the important keywords in understanding machine intelligence in human health and wellness is cognitive bias. Advances in big data and machine learning should not overlook some new threats to enlightened thought, such as the recent trend of social media platforms and commercial recommendation systems being used to manipulate people's inherent cognitive bias. The second important keyword is humanity. Rational thinking, on which early AI researchers had been focused their efforts, is recently and rapidly replacing human thinking by machines. Many people might have begun to believe that irrational thinking is the root of humanity. Empirical and philosophical discussions on AI and humanity would be welcome. This paper describes the detailed motivation, technical, and philosophical challenges of this symposium proposal.

This paper proposes a novel method to estimate sleep stage in real-time with a non-contact device. The proposed method employs the trigonometric function regression model to estimate prospective heart rate from the partially obtained heart rate and calculates the sleep stage from the estimated heart rate. This paper conducts the subject experiment and it is revealed that the proposed method enables to estimate the sleep stage in real-time, in particular the proposed method has the equivalent estimation accuracy as the previous method that estimates the sleep stage according to the entire heart rate during sleeping.

This paper proposes the concept of Well-being computing which is an information technology for improving not only our health as physical aspect but also our happiness as psy-chological aspect, and shows its potential from the sleep perspective. Concretely, this paper introduces “our personal-ized sleep monitoring system” as the well-being computing technologies and shows the following implications as its ef-fectiveness: (1) from the viewpoint of the service based on the real-time sleep, (1-a) good health is provided through a stable sleep of aged person in care house by reducing their sleep disturbance which may be occurred in diaper exchange, while happiness is provided by the smooth diaper exchange when aged person have a deep/light sleep; (1-b) good health is provided through a sufficient sleep time acquired by a fast falling asleep, while happiness is provided by releasing from anxiety of the insufficient sleep such as insomnia; and (2) from the viewpoint of the service based on the long-term sleep, (2-a) good health is provided through a deep sleep by continuing the daytime activities (such as a walking) which contribute to deriving a deep sleep, while happiness is provided by achieving a deep sleep through a change of life style; (2-b) good health is provided through a good sleep by keeping good bed condition (e.g., a change of a pillow or mattress when cotton/spring is deteriorated), while happiness is provided through a discovery of suitable bedding (such as suitable pillow or bed).

This paper describes one of the future images of the sleep monitoring system. The new technology should satisfy the following requirements: (1) noninvasive, (2) low cost and (3) long-term monitoring. What we propose here is the sleep monitoring system based on the human body vibrations sensed by the mattress type pressure sensors that gradually improves its estimation performance to the particular user by learning collected data and reconstructing its classifier.%In order to learn the data, however, the system needs the vibration data mapped to the appropriate sleep stages. As the solution to the problem, we use the existing approximate sleep stage estimation method. The experimental results reveal that (1)there is only a slightly difference between the accuracies of the two classifiers; the one trained the original dataset plus PSG based sleep stage labeled data; the other one trained the original dataset plus approximate sleep stage labeled data; (2 )Adding a particular user's several days data to the training data improves the accuracy of the original classifiers. The REM estimation accuracy is 87% in maximum. From those results, the contribution of this research is suggesting the way to personalize sleep estimation, and proving the effectiveness.

This paper reports a cradle sound system creating and reproducing sounds and music appropriate for human sleep with heartbeat and respiration signals sensed by biological sensors. To get further supporting evidence, we started a study aiming at exploring what sound attributes, such as waveforms, tones, and tempos, are necessary for a sound capable of improving sleep latency. We expected that a cradle sound whose tempo was slightly slower than those of heartbeat and respiration could slow them and could promote natural sleep. Subjects listening to this sound during their sleep showed: (1) Multiple sound types with different tones have an effect to shorten sleep latency. (2) Remarkable effects are observed in subjects with long sleep latency. (3) Sustained synthetic chord used for inducing respiration did not improve sleep latency. (4) There is no correlation between subject’s sensibility evaluation to sound and the effect shortening sleep latency.

This paper aims at developing the ambient intelligence sleep system that can derive a good sleep by providing a personally adapted sound. For this purpose, this paper explores the sounds that have a potential of deriving a good sleep and investigates their effect from the several viewpoints (e.g., the sleep latent time). To promote a good sleep, this paper focuses on heartbeat and respiration which are related to a sleep (i.e., its rate decreases as falling asleep) and proposes the ambient intelligent sleep system that provides the sound adjusted to the heartbeat and/or respiration rates, which are automatically measured by the piezoelectric-based mattress sensor without connecting any devices to human’s body. The human subjective experiments of the six subjects for a nap case and the seven subjects for a night sleep case have revealed the following implications: (1) the new wave sound adjusted to both the heartbeat rate (x 1.05) and respiration rate (x 1.05) can shorten the sleep latent time in a nap case in comparison with no sound or the other four types of the sounds; (2) the combination of the two sound sources (adjusted by the heartbeat and respiration rates) contributes to shortening the sleep latent time in comparison with one sound source; (3) the new wave sound can shorten not only the sleep latent time but also the Non-REM3 latent time in a night sleep case in comparison with no sound; and (4) the new wave sound can keep not only an appropriate sleep cycle but also the very similar sleep cycle from the Non-REM to the next one in a night sleep case in comparison with no sound.