Construction of “Intelligent Bathtub” System
The University of Aizu and ISE have been working together since 2019 to build a watch over system that provides health management and abnormality detection functions. Two patents have already been granted.
Biomedical Information Engineering Lab. has developed several devices that can collect and process biological data.
ISE aims to support the realization of wellbeing for both caregivers and carereceivers with its unique technology. It provides a mechanism to receive integrated notifications from various devices used in the field, reducing operational burdens.
Many Japanese people have the habit of taking a bath every day, but accidents in the bathroom are not uncommon.
Ensuring the safety of the elderly in the bathroom is a social issue that needs to be solved. This system can measure biometric data simply by soaking in the bathtub, analyze these data using machine learning algorithms, and send out an alert if there is a deviation from what is considered comfortable.
*Joint patents:
Patent 7126230 (Bather Monitoring System, filed on February 4, 2022)
Patent 7162232 (Heart Rate Classification Device and Bather Monitoring System, filed on August 5, 2022)
**Vital Statistics by Ministry of Health, Labour and Welfare
According to the Ministry of Health, Labor and Welfare’s Vital Statistics, the number of deaths from Accidental drowning and submersion over the age of 65 has remained at a high level, and in recent years has been higher than that from Transport accidents.
Value proposition of Surmise and Cognitive technology
To estimate a balance between comfort and physical load and to notify a proper bathing time
Is bathing good or bad for the elderly?
Good
Older people who practice bathing in bathtubs are at lower risk of needing nursing care

Press Release No: 157-18-20, Japan Agency for Gerontological Evaluation Study
reference paper:Yagi A, Hayasaka S, Ojima T, Sasaki Y, Tsuji T, Miyaguni Y, Nagamine Y, Namiki T, and Kondo K.(2018). Bathing Frequency and Onset of Functional Disability Among Japanese Older Adults: A Prospective 3-Year Cohort Study From the JAGES. J Epidemiol. 2019 Dec 5;29(12):451-456.
Bad
The number of people who died in bathing exceeds the number of people who died in traffic accidents

based a current population survey, Government Statistics
Elderly people tend to take long baths because they are less likely to feel “blurred” due to the aging of the nervous system, and they feel comfortable
Bathing is good for the elderly, If they can reduce the risk of accidents during bathing!
“Intelligent Bathtub” System
System Characteristics
- Real-time automatic detection of abnormal heartbeat during bathing
- Body comfort estimation during bathing
- Long-term tracking of health condition changes
Using the Electrocardiogram Signal (ECG)-based and independently developed comfort level indicators, the system monitors the physical and mental state of comfort.
When comfort decreases, the bathtub can be unplugged to reduce the risk of drowning.



Joint Research Achievement
S. M. Isuru Niroshana, Satoshi Kuroda, Kazuyuki Tanaka & Wenxi Chen (2022). Beat-wise segmentation of electrocardiogram using adaptive windowing and deep neural network. Scientific Reports
Title: Beat-wise segmentation of electrocardiogram using adaptive windowing and deep neural network
Published: 07 July 2023
Abstract:
Timely detection of anomalies and automatic interpretation of an electrocardiogram (ECG) play a crucial role in many healthcare applications, such as patient monitoring and post treatments. Beat-wise segmentation is one of the essential steps in ensuring the confidence and fidelity of many automatic ECG classification methods. In this sense, we present a reliable ECG beat segmentation technique using a CNN model with an adaptive windowing algorithm. The proposed adaptive windowing algorithm can recognise cardiac cycle events and perform segmentation, including regular and irregular beats from an ECG signal with satisfactorily accurate boundaries.The proposed algorithm was evaluated quantitatively and qualitatively based on the annotations provided with the datasets and beat-wise manual inspection. The algorithm performed satisfactorily well for the MIT-BIH dataset with a 99.08% accuracy and a 99.08% of F1-score in detecting heartbeats along with a 99.25% of accuracy in determining correct boundaries. The proposed method successfully detected heartbeats from the European S-T database with a 98.3% accuracy and 97.4% precision. The algorithm showed 99.4% of accuracy and precision for Fantasia database. In summary, the algorithm’s overall performance on these three datasets suggests a high possibility of applying this algorithm in various applications in ECG analysis, including clinical applications with greater confidence.
About ISE

Information System Engineering Inc.
1F, AD Takadanobaba Building, 35-2, Takadanobaba 3-chome, Shinjuku-ku, Tokyo 169-0075
Website: https://ise.co.jp/en/