IEEE ISCAS 2024

RingConn exhibited at IEEE ISCAS 2024 and demonstrated its latest research results in blood pressure monitoring and sleep apnea

RingConn exhibited at IEEE ISCAS 2024 and demonstrated its latest research results in blood pressure monitoring and sleep apnea

Recently, the 2024 IEEE International Symposium on Circuits and Systems (IEEE ISCAS) was grandly held in Singapore. ISCAS is the flagship conference of the IEEE and is the world's top forum in the field of circuits and systems. It brings together top scholars and researchers from around the world every year to discuss and share the latest technological advancements and promote sustainable development in circuits and systems innovation.

The theme of ISCAS 2024 is "Circuits and Systems for Sustainable Development," covering a wide range of topics including artificial intelligence and deep learning, biomedical circuits and systems, big data processing, digital integrated circuits and systems, and the Internet of Things.

RingConn exhibited at IEEE ISCAS 2024 and demonstrated its latest research results in blood pressure monitoring and sleep apnea

Breakthrough Research by Ninenovo Technology

Ninenovo Technology, in collaboration with Shenzhen University, presented two papers: "A Transformer-Based Deep Learning Model for Sleep Apnea Detection and Application on RingConn Smart Ring" and "A Frequency-domain Features Based Clustering Algorithm for Blood Pressure Estimation with PPG Signal." These papers were accepted at the conference, showcasing the latest technological achievements of the company in intelligent health monitoring through the innovative RingConn Smart Ring.

IEEE ISCAS in Singapore

The first paper, "A Transformer-Based Deep Learning Model for Sleep Apnea Detection and Application on RingConn Smart Ring," explores a new method for detecting Obstructive Sleep Apnea Hypopnea Syndrome (OSAHS) using the RingConn Smart Ring. OSAHS is a common sleep disorder characterized by severe snoring, repeated breathing pauses during sleep, excessive daytime sleepiness, morning headaches, and memory loss. Severe cases can also lead to nighttime asphyxia and cardiovascular problems.

Traditional OSAHS detection requires an overnight examination with bulky polysomnography (PSG) equipment in hospitals. This paper proposes a deep learning model based on Transformer, utilizing the multimodal physiological signals of the RingConn Smart Ring to detect OSAHS.

The model achieved excellent detection results on public datasets with an F1 score of 76.6. The study also evaluated the performance of signal combinations in detecting oxygen desaturation events (DESAT) with the RingConn Smart Ring. Notably, no current research validates OSAHS monitoring based on a smart ring. Thus, the study used data collected from the RingConn Smart Ring for verification and performed PSG-AHI estimation.

Results showed a high correlation (ρ=0.96) between the AHI calculated by the RingConn Smart Ring and PSG-AHI, demonstrating the high accuracy and convenience of the RingConn Smart Ring in medical health monitoring.

The second paper, "A Frequency-domain Features Based Clustering Algorithm for Blood Pressure Estimation with PPG Signal," proposes a clustering algorithm utilizing photoplethysmography (PPG) frequency-domain features. Many studies have focused on estimating blood pressure through PPG waveforms. However, PPG pulses are generated roughly every second, and the features of continuous pulses are similar. Thus, an automated, intelligent method is needed to cluster repetitive signals. For PPG signals with significant differences, an unsupervised method is required to classify PPG pulses into their respective clusters.

The proposed clustering algorithm classifies PPG pulses into specific clusters using PPG frequency-domain features. PPG pulses are processed using fast Fourier transform, extracting frequency, amplitude, phase, real and imaginary parts of the first four frequency components. In the proposed K-Means algorithm, a novel distance function was developed to assess the dissimilarity between two pulses. Additionally, a cluster center merging framework was proposed to address the issue of selecting the K value. The experiment used the MIMIC-II dataset, clustering and merging pulses into 17 clusters.

Results showed that the proposed clustering method successfully identified distinct PPG pulse clusters corresponding to different blood pressure ranges. This finding supports the notion that PPG pulse shape is correlated with blood pressure, enhancing the accuracy and interpretability of blood pressure estimation based on pulse wave analysis. This technology has now been applied to blood pressure monitoring research with the RingConn Smart Ring.

RingConn Smart Ring and Health Management

These research results not only highlight the innovation and technical strength of the RingConn Smart Ring in health management but also further strengthen Ninenovo Technology's mission of "providing uniquely valuable products and services for human health," fully reflecting our commitment and support for innovative research.

Our team will continue to push the boundaries of intelligent wearable technology, using technological innovation to improve human health. We believe that continuous technological breakthroughs will bring users more precise, convenient, and professional health management experiences, contributing to a healthier future.

Reading next

RingConn appeared at IEEE AICAS 2024 in the UAE, and announced its research results on sleep apnea.

Leave a comment

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.